pydantic_ai.tools

AgentDepsT module-attribute

AgentDepsT = TypeVar(
    "AgentDepsT", default=None, contravariant=True
)

Type variable for agent dependencies.

RunContext dataclass

Bases: Generic[AgentDepsT]

Information about the current call.

Source code in pydantic_ai_slim/pydantic_ai/_run_context.py

@dataclasses.dataclass(repr=False, kw_only=True)
class RunContext(Generic[AgentDepsT]):
    """Information about the current call."""

    deps: AgentDepsT
    """Dependencies for the agent."""
    model: Model
    """The model used in this run."""
    usage: RunUsage
    """LLM usage associated with the run."""
    prompt: str | Sequence[_messages.UserContent] | None = None
    """The original user prompt passed to the run."""
    messages: list[_messages.ModelMessage] = field(default_factory=list)
    """Messages exchanged in the conversation so far."""
    tracer: Tracer = field(default_factory=NoOpTracer)
    """The tracer to use for tracing the run."""
    trace_include_content: bool = False
    """Whether to include the content of the messages in the trace."""
    retries: dict[str, int] = field(default_factory=dict)
    """Number of retries for each tool so far."""
    tool_call_id: str | None = None
    """The ID of the tool call."""
    tool_name: str | None = None
    """Name of the tool being called."""
    retry: int = 0
    """Number of retries so far."""
    run_step: int = 0
    """The current step in the run."""
    tool_call_approved: bool = False
    """Whether a tool call that required approval has now been approved."""

    __repr__ = _utils.dataclasses_no_defaults_repr

deps instance-attribute

deps: AgentDepsT

Dependencies for the agent.

model instance-attribute

model: Model

The model used in this run.

usage instance-attribute

usage: RunUsage

LLM usage associated with the run.

prompt class-attribute instance-attribute

prompt: str | Sequence[UserContent] | None = None

The original user prompt passed to the run.

messages class-attribute instance-attribute

messages: list[ModelMessage] = field(default_factory=list)

Messages exchanged in the conversation so far.

tracer class-attribute instance-attribute

tracer: Tracer = field(default_factory=NoOpTracer)

The tracer to use for tracing the run.

trace_include_content class-attribute instance-attribute

trace_include_content: bool = False

Whether to include the content of the messages in the trace.

retries class-attribute instance-attribute

retries: dict[str, int] = field(default_factory=dict)

Number of retries for each tool so far.

tool_call_id class-attribute instance-attribute

tool_call_id: str | None = None

The ID of the tool call.

tool_name class-attribute instance-attribute

tool_name: str | None = None

Name of the tool being called.

retry class-attribute instance-attribute

retry: int = 0

Number of retries so far.

run_step class-attribute instance-attribute

run_step: int = 0

The current step in the run.

tool_call_approved class-attribute instance-attribute

tool_call_approved: bool = False

Whether a tool call that required approval has now been approved.

ToolParams module-attribute

ToolParams = ParamSpec('ToolParams', default=...)

Retrieval function param spec.

SystemPromptFunc module-attribute

SystemPromptFunc: TypeAlias = (
    Callable[[RunContext[AgentDepsT]], str]
    | Callable[[RunContext[AgentDepsT]], Awaitable[str]]
    | Callable[[], str]
    | Callable[[], Awaitable[str]]
)

A function that may or maybe not take RunContext as an argument, and may or may not be async.

Usage SystemPromptFunc[AgentDepsT].

ToolFuncContext module-attribute

ToolFuncContext: TypeAlias = Callable[
    Concatenate[RunContext[AgentDepsT], ToolParams], Any
]

A tool function that takes RunContext as the first argument.

Usage ToolContextFunc[AgentDepsT, ToolParams].

ToolFuncPlain module-attribute

ToolFuncPlain: TypeAlias = Callable[ToolParams, Any]

A tool function that does not take RunContext as the first argument.

Usage ToolPlainFunc[ToolParams].

ToolFuncEither module-attribute

ToolFuncEither: TypeAlias = (
    ToolFuncContext[AgentDepsT, ToolParams]
    | ToolFuncPlain[ToolParams]
)

Either kind of tool function.

This is just a union of ToolFuncContext and ToolFuncPlain.

Usage ToolFuncEither[AgentDepsT, ToolParams].

ToolPrepareFunc module-attribute

ToolPrepareFunc: TypeAlias = Callable[
    [RunContext[AgentDepsT], "ToolDefinition"],
    Awaitable["ToolDefinition | None"],
]

Definition of a function that can prepare a tool definition at call time.

See tool docs for more information.

Example — here only_if_42 is valid as a ToolPrepareFunc:

from pydantic_ai import RunContext, Tool
from pydantic_ai.tools import ToolDefinition

async def only_if_42(
    ctx: RunContext[int], tool_def: ToolDefinition
) -> ToolDefinition | None:
    if ctx.deps == 42:
        return tool_def

def hitchhiker(ctx: RunContext[int], answer: str) -> str:
    return f'{ctx.deps} {answer}'

hitchhiker = Tool(hitchhiker, prepare=only_if_42)

Usage ToolPrepareFunc[AgentDepsT].

ToolsPrepareFunc module-attribute

ToolsPrepareFunc: TypeAlias = Callable[
    [RunContext[AgentDepsT], list["ToolDefinition"]],
    Awaitable["list[ToolDefinition] | None"],
]

Definition of a function that can prepare the tool definition of all tools for each step. This is useful if you want to customize the definition of multiple tools or you want to register a subset of tools for a given step.

Example — here turn_on_strict_if_openai is valid as a ToolsPrepareFunc:

from dataclasses import replace

from pydantic_ai import Agent, RunContext
from pydantic_ai.tools import ToolDefinition


async def turn_on_strict_if_openai(
    ctx: RunContext[None], tool_defs: list[ToolDefinition]
) -> list[ToolDefinition] | None:
    if ctx.model.system == 'openai':
        return [replace(tool_def, strict=True) for tool_def in tool_defs]
    return tool_defs

agent = Agent('openai:gpt-4o', prepare_tools=turn_on_strict_if_openai)

Usage ToolsPrepareFunc[AgentDepsT].

DocstringFormat module-attribute

DocstringFormat: TypeAlias = Literal[
    "google", "numpy", "sphinx", "auto"
]

Supported docstring formats.

• 'google' — Google-style docstrings.
• 'numpy' — Numpy-style docstrings.
• 'sphinx' — Sphinx-style docstrings.
• 'auto' — Automatically infer the format based on the structure of the docstring.

DeferredToolRequests dataclass

Tool calls that require approval or external execution.

This can be used as an agent's output_type and will be used as the output of the agent run if the model called any deferred tools.

Results can be passed to the next agent run using a DeferredToolResults object with the same tool call IDs.

See deferred tools docs for more information.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@dataclass(kw_only=True)
class DeferredToolRequests:
    """Tool calls that require approval or external execution.

    This can be used as an agent's `output_type` and will be used as the output of the agent run if the model called any deferred tools.

    Results can be passed to the next agent run using a [`DeferredToolResults`][pydantic_ai.tools.DeferredToolResults] object with the same tool call IDs.

    See [deferred tools docs](../deferred-tools.md#deferred-tools) for more information.
    """

    calls: list[ToolCallPart] = field(default_factory=list)
    """Tool calls that require external execution."""
    approvals: list[ToolCallPart] = field(default_factory=list)
    """Tool calls that require human-in-the-loop approval."""

calls class-attribute instance-attribute

calls: list[ToolCallPart] = field(default_factory=list)

Tool calls that require external execution.

approvals class-attribute instance-attribute

approvals: list[ToolCallPart] = field(default_factory=list)

Tool calls that require human-in-the-loop approval.

ToolApproved dataclass

Indicates that a tool call has been approved and that the tool function should be executed.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@dataclass(kw_only=True)
class ToolApproved:
    """Indicates that a tool call has been approved and that the tool function should be executed."""

    override_args: dict[str, Any] | None = None
    """Optional tool call arguments to use instead of the original arguments."""

    kind: Literal['tool-approved'] = 'tool-approved'

override_args class-attribute instance-attribute

override_args: dict[str, Any] | None = None

Optional tool call arguments to use instead of the original arguments.

ToolDenied dataclass

Indicates that a tool call has been denied and that a denial message should be returned to the model.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@dataclass
class ToolDenied:
    """Indicates that a tool call has been denied and that a denial message should be returned to the model."""

    message: str = 'The tool call was denied.'
    """The message to return to the model."""

    _: KW_ONLY

    kind: Literal['tool-denied'] = 'tool-denied'

message class-attribute instance-attribute

message: str = 'The tool call was denied.'

The message to return to the model.

DeferredToolResults dataclass

Results for deferred tool calls from a previous run that required approval or external execution.

The tool call IDs need to match those from the DeferredToolRequests output object from the previous run.

See deferred tools docs for more information.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@dataclass(kw_only=True)
class DeferredToolResults:
    """Results for deferred tool calls from a previous run that required approval or external execution.

    The tool call IDs need to match those from the [`DeferredToolRequests`][pydantic_ai.output.DeferredToolRequests] output object from the previous run.

    See [deferred tools docs](../deferred-tools.md#deferred-tools) for more information.
    """

    calls: dict[str, DeferredToolCallResult | Any] = field(default_factory=dict)
    """Map of tool call IDs to results for tool calls that required external execution."""
    approvals: dict[str, bool | DeferredToolApprovalResult] = field(default_factory=dict)
    """Map of tool call IDs to results for tool calls that required human-in-the-loop approval."""

calls class-attribute instance-attribute

calls: dict[str, DeferredToolCallResult | Any] = field(
    default_factory=dict
)

Map of tool call IDs to results for tool calls that required external execution.

approvals class-attribute instance-attribute

approvals: dict[str, bool | DeferredToolApprovalResult] = (
    field(default_factory=dict)
)

Map of tool call IDs to results for tool calls that required human-in-the-loop approval.

Tool dataclass

Bases: Generic[AgentDepsT]

A tool function for an agent.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@dataclass(init=False)
class Tool(Generic[AgentDepsT]):
    """A tool function for an agent."""

    function: ToolFuncEither[AgentDepsT]
    takes_ctx: bool
    max_retries: int | None
    name: str
    description: str | None
    prepare: ToolPrepareFunc[AgentDepsT] | None
    docstring_format: DocstringFormat
    require_parameter_descriptions: bool
    strict: bool | None
    sequential: bool
    requires_approval: bool
    function_schema: _function_schema.FunctionSchema
    """
    The base JSON schema for the tool's parameters.

    This schema may be modified by the `prepare` function or by the Model class prior to including it in an API request.
    """

    def __init__(
        self,
        function: ToolFuncEither[AgentDepsT],
        *,
        takes_ctx: bool | None = None,
        max_retries: int | None = None,
        name: str | None = None,
        description: str | None = None,
        prepare: ToolPrepareFunc[AgentDepsT] | None = None,
        docstring_format: DocstringFormat = 'auto',
        require_parameter_descriptions: bool = False,
        schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
        strict: bool | None = None,
        sequential: bool = False,
        requires_approval: bool = False,
        function_schema: _function_schema.FunctionSchema | None = None,
    ):
        """Create a new tool instance.

        Example usage:

        ```python {noqa="I001"}
        from pydantic_ai import Agent, RunContext, Tool

        async def my_tool(ctx: RunContext[int], x: int, y: int) -> str:
            return f'{ctx.deps} {x} {y}'

        agent = Agent('test', tools=[Tool(my_tool)])
        ```

        or with a custom prepare method:

        ```python {noqa="I001"}

        from pydantic_ai import Agent, RunContext, Tool
        from pydantic_ai.tools import ToolDefinition

        async def my_tool(ctx: RunContext[int], x: int, y: int) -> str:
            return f'{ctx.deps} {x} {y}'

        async def prep_my_tool(
            ctx: RunContext[int], tool_def: ToolDefinition
        ) -> ToolDefinition | None:
            # only register the tool if `deps == 42`
            if ctx.deps == 42:
                return tool_def

        agent = Agent('test', tools=[Tool(my_tool, prepare=prep_my_tool)])
        ```


        Args:
            function: The Python function to call as the tool.
            takes_ctx: Whether the function takes a [`RunContext`][pydantic_ai.tools.RunContext] first argument,
                this is inferred if unset.
            max_retries: Maximum number of retries allowed for this tool, set to the agent default if `None`.
            name: Name of the tool, inferred from the function if `None`.
            description: Description of the tool, inferred from the function if `None`.
            prepare: custom method to prepare the tool definition for each step, return `None` to omit this
                tool from a given step. This is useful if you want to customise a tool at call time,
                or omit it completely from a step. See [`ToolPrepareFunc`][pydantic_ai.tools.ToolPrepareFunc].
            docstring_format: The format of the docstring, see [`DocstringFormat`][pydantic_ai.tools.DocstringFormat].
                Defaults to `'auto'`, such that the format is inferred from the structure of the docstring.
            require_parameter_descriptions: If True, raise an error if a parameter description is missing. Defaults to False.
            schema_generator: The JSON schema generator class to use. Defaults to `GenerateToolJsonSchema`.
            strict: Whether to enforce JSON schema compliance (only affects OpenAI).
                See [`ToolDefinition`][pydantic_ai.tools.ToolDefinition] for more info.
            sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.
            requires_approval: Whether this tool requires human-in-the-loop approval. Defaults to False.
                See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
            function_schema: The function schema to use for the tool. If not provided, it will be generated.
        """
        self.function = function
        self.function_schema = function_schema or _function_schema.function_schema(
            function,
            schema_generator,
            takes_ctx=takes_ctx,
            docstring_format=docstring_format,
            require_parameter_descriptions=require_parameter_descriptions,
        )
        self.takes_ctx = self.function_schema.takes_ctx
        self.max_retries = max_retries
        self.name = name or function.__name__
        self.description = description or self.function_schema.description
        self.prepare = prepare
        self.docstring_format = docstring_format
        self.require_parameter_descriptions = require_parameter_descriptions
        self.strict = strict
        self.sequential = sequential
        self.requires_approval = requires_approval

    @classmethod
    def from_schema(
        cls,
        function: Callable[..., Any],
        name: str,
        description: str | None,
        json_schema: JsonSchemaValue,
        takes_ctx: bool = False,
        sequential: bool = False,
    ) -> Self:
        """Creates a Pydantic tool from a function and a JSON schema.

        Args:
            function: The function to call.
                This will be called with keywords only, and no validation of
                the arguments will be performed.
            name: The unique name of the tool that clearly communicates its purpose
            description: Used to tell the model how/when/why to use the tool.
                You can provide few-shot examples as a part of the description.
            json_schema: The schema for the function arguments
            takes_ctx: An optional boolean parameter indicating whether the function
                accepts the context object as an argument.
            sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.

        Returns:
            A Pydantic tool that calls the function
        """
        function_schema = _function_schema.FunctionSchema(
            function=function,
            description=description,
            validator=SchemaValidator(schema=core_schema.any_schema()),
            json_schema=json_schema,
            takes_ctx=takes_ctx,
            is_async=_utils.is_async_callable(function),
        )

        return cls(
            function,
            takes_ctx=takes_ctx,
            name=name,
            description=description,
            function_schema=function_schema,
            sequential=sequential,
        )

    @property
    def tool_def(self):
        return ToolDefinition(
            name=self.name,
            description=self.description,
            parameters_json_schema=self.function_schema.json_schema,
            strict=self.strict,
            sequential=self.sequential,
        )

    async def prepare_tool_def(self, ctx: RunContext[AgentDepsT]) -> ToolDefinition | None:
        """Get the tool definition.

        By default, this method creates a tool definition, then either returns it, or calls `self.prepare`
        if it's set.

        Returns:
            return a `ToolDefinition` or `None` if the tools should not be registered for this run.
        """
        base_tool_def = self.tool_def

        if self.requires_approval and not ctx.tool_call_approved:
            base_tool_def = replace(base_tool_def, kind='unapproved')

        if self.prepare is not None:
            return await self.prepare(ctx, base_tool_def)
        else:
            return base_tool_def

__init__

__init__(
    function: ToolFuncEither[AgentDepsT],
    *,
    takes_ctx: bool | None = None,
    max_retries: int | None = None,
    name: str | None = None,
    description: str | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    docstring_format: DocstringFormat = "auto",
    require_parameter_descriptions: bool = False,
    schema_generator: type[
        GenerateJsonSchema
    ] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    function_schema: FunctionSchema | None = None
)

Create a new tool instance.

Example usage:

from pydantic_ai import Agent, RunContext, Tool

async def my_tool(ctx: RunContext[int], x: int, y: int) -> str:
    return f'{ctx.deps} {x} {y}'

agent = Agent('test', tools=[Tool(my_tool)])

or with a custom prepare method:

from pydantic_ai import Agent, RunContext, Tool
from pydantic_ai.tools import ToolDefinition

async def my_tool(ctx: RunContext[int], x: int, y: int) -> str:
    return f'{ctx.deps} {x} {y}'

async def prep_my_tool(
    ctx: RunContext[int], tool_def: ToolDefinition
) -> ToolDefinition | None:
    # only register the tool if `deps == 42`
    if ctx.deps == 42:
        return tool_def

agent = Agent('test', tools=[Tool(my_tool, prepare=prep_my_tool)])

Parameters:

Name	Type	Description	Default
function	ToolFuncEither[AgentDepsT]	The Python function to call as the tool.	required
takes_ctx	bool | None	Whether the function takes a RunContext first argument, this is inferred if unset.	None
max_retries	int | None	Maximum number of retries allowed for this tool, set to the agent default if None.	None
name	str | None	Name of the tool, inferred from the function if None.	None
description	str | None	Description of the tool, inferred from the function if None.	None
prepare	ToolPrepareFunc[AgentDepsT] | None	custom method to prepare the tool definition for each step, return None to omit this tool from a given step. This is useful if you want to customise a tool at call time, or omit it completely from a step. See ToolPrepareFunc.	None
docstring_format	DocstringFormat	The format of the docstring, see DocstringFormat. Defaults to 'auto', such that the format is inferred from the structure of the docstring.	'auto'
require_parameter_descriptions	bool	If True, raise an error if a parameter description is missing. Defaults to False.	False
schema_generator	type[GenerateJsonSchema]	The JSON schema generator class to use. Defaults to GenerateToolJsonSchema.	GenerateToolJsonSchema
strict	bool | None	Whether to enforce JSON schema compliance (only affects OpenAI). See ToolDefinition for more info.	None
sequential	bool	Whether the function requires a sequential/serial execution environment. Defaults to False.	False
requires_approval	bool	Whether this tool requires human-in-the-loop approval. Defaults to False. See the tools documentation for more info.	False
function_schema	FunctionSchema | None	The function schema to use for the tool. If not provided, it will be generated.	None

Source code in pydantic_ai_slim/pydantic_ai/tools.py

def __init__(
    self,
    function: ToolFuncEither[AgentDepsT],
    *,
    takes_ctx: bool | None = None,
    max_retries: int | None = None,
    name: str | None = None,
    description: str | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    docstring_format: DocstringFormat = 'auto',
    require_parameter_descriptions: bool = False,
    schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    function_schema: _function_schema.FunctionSchema | None = None,
):
    """Create a new tool instance.

    Example usage:

    ```python {noqa="I001"}
    from pydantic_ai import Agent, RunContext, Tool

    async def my_tool(ctx: RunContext[int], x: int, y: int) -> str:
        return f'{ctx.deps} {x} {y}'

    agent = Agent('test', tools=[Tool(my_tool)])
    ```

    or with a custom prepare method:

    ```python {noqa="I001"}

    from pydantic_ai import Agent, RunContext, Tool
    from pydantic_ai.tools import ToolDefinition

    async def my_tool(ctx: RunContext[int], x: int, y: int) -> str:
        return f'{ctx.deps} {x} {y}'

    async def prep_my_tool(
        ctx: RunContext[int], tool_def: ToolDefinition
    ) -> ToolDefinition | None:
        # only register the tool if `deps == 42`
        if ctx.deps == 42:
            return tool_def

    agent = Agent('test', tools=[Tool(my_tool, prepare=prep_my_tool)])
    ```


    Args:
        function: The Python function to call as the tool.
        takes_ctx: Whether the function takes a [`RunContext`][pydantic_ai.tools.RunContext] first argument,
            this is inferred if unset.
        max_retries: Maximum number of retries allowed for this tool, set to the agent default if `None`.
        name: Name of the tool, inferred from the function if `None`.
        description: Description of the tool, inferred from the function if `None`.
        prepare: custom method to prepare the tool definition for each step, return `None` to omit this
            tool from a given step. This is useful if you want to customise a tool at call time,
            or omit it completely from a step. See [`ToolPrepareFunc`][pydantic_ai.tools.ToolPrepareFunc].
        docstring_format: The format of the docstring, see [`DocstringFormat`][pydantic_ai.tools.DocstringFormat].
            Defaults to `'auto'`, such that the format is inferred from the structure of the docstring.
        require_parameter_descriptions: If True, raise an error if a parameter description is missing. Defaults to False.
        schema_generator: The JSON schema generator class to use. Defaults to `GenerateToolJsonSchema`.
        strict: Whether to enforce JSON schema compliance (only affects OpenAI).
            See [`ToolDefinition`][pydantic_ai.tools.ToolDefinition] for more info.
        sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.
        requires_approval: Whether this tool requires human-in-the-loop approval. Defaults to False.
            See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
        function_schema: The function schema to use for the tool. If not provided, it will be generated.
    """
    self.function = function
    self.function_schema = function_schema or _function_schema.function_schema(
        function,
        schema_generator,
        takes_ctx=takes_ctx,
        docstring_format=docstring_format,
        require_parameter_descriptions=require_parameter_descriptions,
    )
    self.takes_ctx = self.function_schema.takes_ctx
    self.max_retries = max_retries
    self.name = name or function.__name__
    self.description = description or self.function_schema.description
    self.prepare = prepare
    self.docstring_format = docstring_format
    self.require_parameter_descriptions = require_parameter_descriptions
    self.strict = strict
    self.sequential = sequential
    self.requires_approval = requires_approval

function_schema instance-attribute

function_schema: FunctionSchema = (
    function_schema
    or function_schema(
        function,
        schema_generator,
        takes_ctx=takes_ctx,
        docstring_format=docstring_format,
        require_parameter_descriptions=require_parameter_descriptions,
    )
)

The base JSON schema for the tool's parameters.

This schema may be modified by the prepare function or by the Model class prior to including it in an API request.

from_schema classmethod

from_schema(
    function: Callable[..., Any],
    name: str,
    description: str | None,
    json_schema: JsonSchemaValue,
    takes_ctx: bool = False,
    sequential: bool = False,
) -> Self

Creates a Pydantic tool from a function and a JSON schema.

Parameters:

Name	Type	Description	Default
function	Callable[..., Any]	The function to call. This will be called with keywords only, and no validation of the arguments will be performed.	required
name	str	The unique name of the tool that clearly communicates its purpose	required
description	str | None	Used to tell the model how/when/why to use the tool. You can provide few-shot examples as a part of the description.	required
json_schema	JsonSchemaValue	The schema for the function arguments	required
takes_ctx	bool	An optional boolean parameter indicating whether the function accepts the context object as an argument.	False
sequential	bool	Whether the function requires a sequential/serial execution environment. Defaults to False.	False

Returns:

Type	Description
Self	A Pydantic tool that calls the function

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@classmethod
def from_schema(
    cls,
    function: Callable[..., Any],
    name: str,
    description: str | None,
    json_schema: JsonSchemaValue,
    takes_ctx: bool = False,
    sequential: bool = False,
) -> Self:
    """Creates a Pydantic tool from a function and a JSON schema.

    Args:
        function: The function to call.
            This will be called with keywords only, and no validation of
            the arguments will be performed.
        name: The unique name of the tool that clearly communicates its purpose
        description: Used to tell the model how/when/why to use the tool.
            You can provide few-shot examples as a part of the description.
        json_schema: The schema for the function arguments
        takes_ctx: An optional boolean parameter indicating whether the function
            accepts the context object as an argument.
        sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.

    Returns:
        A Pydantic tool that calls the function
    """
    function_schema = _function_schema.FunctionSchema(
        function=function,
        description=description,
        validator=SchemaValidator(schema=core_schema.any_schema()),
        json_schema=json_schema,
        takes_ctx=takes_ctx,
        is_async=_utils.is_async_callable(function),
    )

    return cls(
        function,
        takes_ctx=takes_ctx,
        name=name,
        description=description,
        function_schema=function_schema,
        sequential=sequential,
    )

prepare_tool_def async

prepare_tool_def(
    ctx: RunContext[AgentDepsT],
) -> ToolDefinition | None

Get the tool definition.

By default, this method creates a tool definition, then either returns it, or calls self.prepare if it's set.

Returns:

Type	Description
ToolDefinition | None	return a ToolDefinition or None if the tools should not be registered for this run.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

async def prepare_tool_def(self, ctx: RunContext[AgentDepsT]) -> ToolDefinition | None:
    """Get the tool definition.

    By default, this method creates a tool definition, then either returns it, or calls `self.prepare`
    if it's set.

    Returns:
        return a `ToolDefinition` or `None` if the tools should not be registered for this run.
    """
    base_tool_def = self.tool_def

    if self.requires_approval and not ctx.tool_call_approved:
        base_tool_def = replace(base_tool_def, kind='unapproved')

    if self.prepare is not None:
        return await self.prepare(ctx, base_tool_def)
    else:
        return base_tool_def

ObjectJsonSchema module-attribute

ObjectJsonSchema: TypeAlias = dict[str, Any]

Type representing JSON schema of an object, e.g. where "type": "object".

This type is used to define tools parameters (aka arguments) in ToolDefinition.

With PEP-728 this should be a TypedDict with type: Literal['object'], and extra_parts=Any

ToolDefinition dataclass

Definition of a tool passed to a model.

This is used for both function tools and output tools.

Source code in pydantic_ai_slim/pydantic_ai/tools.py

@dataclass(repr=False, kw_only=True)
class ToolDefinition:
    """Definition of a tool passed to a model.

    This is used for both function tools and output tools.
    """

    name: str
    """The name of the tool."""

    parameters_json_schema: ObjectJsonSchema = field(default_factory=lambda: {'type': 'object', 'properties': {}})
    """The JSON schema for the tool's parameters."""

    description: str | None = None
    """The description of the tool."""

    outer_typed_dict_key: str | None = None
    """The key in the outer [TypedDict] that wraps an output tool.

    This will only be set for output tools which don't have an `object` JSON schema.
    """

    strict: bool | None = None
    """Whether to enforce (vendor-specific) strict JSON schema validation for tool calls.

    Setting this to `True` while using a supported model generally imposes some restrictions on the tool's JSON schema
    in exchange for guaranteeing the API responses strictly match that schema.

    When `False`, the model may be free to generate other properties or types (depending on the vendor).
    When `None` (the default), the value will be inferred based on the compatibility of the parameters_json_schema.

    Note: this is currently only supported by OpenAI models.
    """

    sequential: bool = False
    """Whether this tool requires a sequential/serial execution environment."""

    kind: ToolKind = field(default='function')
    """The kind of tool:

    - `'function'`: a tool that will be executed by Pydantic AI during an agent run and has its result returned to the model
    - `'output'`: a tool that passes through an output value that ends the run
    - `'external'`: a tool whose result will be produced outside of the Pydantic AI agent run in which it was called, because it depends on an upstream service (or user) or could take longer to generate than it's reasonable to keep the agent process running.
        See the [tools documentation](../deferred-tools.md#deferred-tools) for more info.
    - `'unapproved'`: a tool that requires human-in-the-loop approval.
        See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
    """

    @property
    def defer(self) -> bool:
        """Whether calls to this tool will be deferred.

        See the [tools documentation](../deferred-tools.md#deferred-tools) for more info.
        """
        return self.kind in ('external', 'unapproved')

    __repr__ = _utils.dataclasses_no_defaults_repr

name instance-attribute

name: str

The name of the tool.

parameters_json_schema class-attribute instance-attribute

parameters_json_schema: ObjectJsonSchema = field(
    default_factory=lambda: {
        "type": "object",
        "properties": {},
    }
)

The JSON schema for the tool's parameters.

description class-attribute instance-attribute

description: str | None = None

The description of the tool.

outer_typed_dict_key class-attribute instance-attribute

outer_typed_dict_key: str | None = None

The key in the outer [TypedDict] that wraps an output tool.

This will only be set for output tools which don't have an object JSON schema.

strict class-attribute instance-attribute

strict: bool | None = None

Whether to enforce (vendor-specific) strict JSON schema validation for tool calls.

Setting this to True while using a supported model generally imposes some restrictions on the tool's JSON schema in exchange for guaranteeing the API responses strictly match that schema.

When False, the model may be free to generate other properties or types (depending on the vendor). When None (the default), the value will be inferred based on the compatibility of the parameters_json_schema.

Note: this is currently only supported by OpenAI models.

sequential class-attribute instance-attribute

sequential: bool = False

Whether this tool requires a sequential/serial execution environment.

kind class-attribute instance-attribute

kind: ToolKind = field(default='function')

The kind of tool:

• 'function': a tool that will be executed by Pydantic AI during an agent run and has its result returned to the model
• 'output': a tool that passes through an output value that ends the run
• 'external': a tool whose result will be produced outside of the Pydantic AI agent run in which it was called, because it depends on an upstream service (or user) or could take longer to generate than it's reasonable to keep the agent process running. See the tools documentation for more info.
• 'unapproved': a tool that requires human-in-the-loop approval. See the tools documentation for more info.

defer property

defer: bool

Whether calls to this tool will be deferred.

See the tools documentation for more info.