Tools

Tool module-attribute

Tool = Union[
    FunctionTool,
    FileSearchTool,
    WebSearchTool,
    ComputerTool,
]

A tool that can be used in an agent.

FunctionTool dataclass

A tool that wraps a function. In most cases, you should use the function_tool helpers to create a FunctionTool, as they let you easily wrap a Python function.

Source code in src/cai/sdk/agents/tool.py

@dataclass
class FunctionTool:
    """A tool that wraps a function. In most cases, you should use  the `function_tool` helpers to
    create a FunctionTool, as they let you easily wrap a Python function.
    """

    name: str
    """The name of the tool, as shown to the LLM. Generally the name of the function."""

    description: str
    """A description of the tool, as shown to the LLM."""

    params_json_schema: dict[str, Any]
    """The JSON schema for the tool's parameters."""

    on_invoke_tool: Callable[[RunContextWrapper[Any], str], Awaitable[Any]]
    """A function that invokes the tool with the given context and parameters. The params passed
    are:
    1. The tool run context.
    2. The arguments from the LLM, as a JSON string.

    You must return a string representation of the tool output, or something we can call `str()` on.
    In case of errors, you can either raise an Exception (which will cause the run to fail) or
    return a string error message (which will be sent back to the LLM).
    """

    strict_json_schema: bool = True
    """Whether the JSON schema is in strict mode. We **strongly** recommend setting this to True,
    as it increases the likelihood of correct JSON input."""

name instance-attribute

name: str

The name of the tool, as shown to the LLM. Generally the name of the function.

description instance-attribute

description: str

A description of the tool, as shown to the LLM.

params_json_schema instance-attribute

params_json_schema: dict[str, Any]

The JSON schema for the tool's parameters.

on_invoke_tool instance-attribute

on_invoke_tool: Callable[
    [RunContextWrapper[Any], str], Awaitable[Any]
]

A function that invokes the tool with the given context and parameters. The params passed are: 1. The tool run context. 2. The arguments from the LLM, as a JSON string.

You must return a string representation of the tool output, or something we can call str() on. In case of errors, you can either raise an Exception (which will cause the run to fail) or return a string error message (which will be sent back to the LLM).

strict_json_schema class-attribute instance-attribute

strict_json_schema: bool = True

Whether the JSON schema is in strict mode. We strongly recommend setting this to True, as it increases the likelihood of correct JSON input.

function_tool

function_tool(
    func: ToolFunction[...],
    *,
    name_override: str | None = None,
    description_override: str | None = None,
    docstring_style: DocstringStyle | None = None,
    use_docstring_info: bool = True,
    failure_error_function: ToolErrorFunction | None = None,
    strict_mode: bool = True,
) -> FunctionTool

function_tool(
    *,
    name_override: str | None = None,
    description_override: str | None = None,
    docstring_style: DocstringStyle | None = None,
    use_docstring_info: bool = True,
    failure_error_function: ToolErrorFunction | None = None,
    strict_mode: bool = True,
) -> Callable[[ToolFunction[...]], FunctionTool]

function_tool(
    func: ToolFunction[...] | None = None,
    *,
    name_override: str | None = None,
    description_override: str | None = None,
    docstring_style: DocstringStyle | None = None,
    use_docstring_info: bool = True,
    failure_error_function: ToolErrorFunction
    | None = default_tool_error_function,
    strict_mode: bool = True,
) -> (
    FunctionTool
    | Callable[[ToolFunction[...]], FunctionTool]
)

Decorator to create a FunctionTool from a function. By default, we will: 1. Parse the function signature to create a JSON schema for the tool's parameters. 2. Use the function's docstring to populate the tool's description. 3. Use the function's docstring to populate argument descriptions. The docstring style is detected automatically, but you can override it.

If the function takes a RunContextWrapper as the first argument, it must match the context type of the agent that uses the tool.

Parameters:

Name	Type	Description	Default
func	ToolFunction[...] | None	The function to wrap.	None
name_override	str | None	If provided, use this name for the tool instead of the function's name.	None
description_override	str | None	If provided, use this description for the tool instead of the function's docstring.	None
docstring_style	DocstringStyle | None	If provided, use this style for the tool's docstring. If not provided, we will attempt to auto-detect the style.	None
use_docstring_info	bool	If True, use the function's docstring to populate the tool's description and argument descriptions.	True
failure_error_function	ToolErrorFunction | None	If provided, use this function to generate an error message when the tool call fails. The error message is sent to the LLM. If you pass None, then no error message will be sent and instead an Exception will be raised.	default_tool_error_function
strict_mode	bool	Whether to enable strict mode for the tool's JSON schema. We strongly recommend setting this to True, as it increases the likelihood of correct JSON input. If False, it allows non-strict JSON schemas. For example, if a parameter has a default value, it will be optional, additional properties are allowed, etc. See here for more: https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses#supported-schemas	True

Source code in src/cai/sdk/agents/tool.py

def function_tool(
    func: ToolFunction[...] | None = None,
    *,
    name_override: str | None = None,
    description_override: str | None = None,
    docstring_style: DocstringStyle | None = None,
    use_docstring_info: bool = True,
    failure_error_function: ToolErrorFunction | None = default_tool_error_function,
    strict_mode: bool = True,
) -> FunctionTool | Callable[[ToolFunction[...]], FunctionTool]:
    """
    Decorator to create a FunctionTool from a function. By default, we will:
    1. Parse the function signature to create a JSON schema for the tool's parameters.
    2. Use the function's docstring to populate the tool's description.
    3. Use the function's docstring to populate argument descriptions.
    The docstring style is detected automatically, but you can override it.

    If the function takes a `RunContextWrapper` as the first argument, it *must* match the
    context type of the agent that uses the tool.

    Args:
        func: The function to wrap.
        name_override: If provided, use this name for the tool instead of the function's name.
        description_override: If provided, use this description for the tool instead of the
            function's docstring.
        docstring_style: If provided, use this style for the tool's docstring. If not provided,
            we will attempt to auto-detect the style.
        use_docstring_info: If True, use the function's docstring to populate the tool's
            description and argument descriptions.
        failure_error_function: If provided, use this function to generate an error message when
            the tool call fails. The error message is sent to the LLM. If you pass None, then no
            error message will be sent and instead an Exception will be raised.
        strict_mode: Whether to enable strict mode for the tool's JSON schema. We *strongly*
            recommend setting this to True, as it increases the likelihood of correct JSON input.
            If False, it allows non-strict JSON schemas. For example, if a parameter has a default
            value, it will be optional, additional properties are allowed, etc. See here for more:
            https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses#supported-schemas
    """

    def _create_function_tool(the_func: ToolFunction[...]) -> FunctionTool:
        schema = function_schema(
            func=the_func,
            name_override=name_override,
            description_override=description_override,
            docstring_style=docstring_style,
            use_docstring_info=use_docstring_info,
            strict_json_schema=strict_mode,
        )

        async def _on_invoke_tool_impl(ctx: RunContextWrapper[Any], input: str) -> Any:
            try:
                json_data: dict[str, Any] = json.loads(input) if input else {}
            except Exception as e:
                if _debug.DONT_LOG_TOOL_DATA:
                    logger.debug(f"Invalid JSON input for tool {schema.name}")
                else:
                    logger.debug(f"Invalid JSON input for tool {schema.name}: {input}")
                raise ModelBehaviorError(
                    f"Invalid JSON input for tool {schema.name}: {input}"
                ) from e

            if _debug.DONT_LOG_TOOL_DATA:
                logger.debug(f"Invoking tool {schema.name}")
            else:
                logger.debug(f"Invoking tool {schema.name} with input {input}")

            try:
                parsed = (
                    schema.params_pydantic_model(**json_data)
                    if json_data
                    else schema.params_pydantic_model()
                )
            except ValidationError as e:
                raise ModelBehaviorError(f"Invalid JSON input for tool {schema.name}: {e}") from e

            args, kwargs_dict = schema.to_call_args(parsed)

            if not _debug.DONT_LOG_TOOL_DATA:
                logger.debug(f"Tool call args: {args}, kwargs: {kwargs_dict}")

            if inspect.iscoroutinefunction(the_func):
                if schema.takes_context:
                    result = await the_func(ctx, *args, **kwargs_dict)
                else:
                    result = await the_func(*args, **kwargs_dict)
            else:
                if schema.takes_context:
                    result = the_func(ctx, *args, **kwargs_dict)
                else:
                    result = the_func(*args, **kwargs_dict)

            if _debug.DONT_LOG_TOOL_DATA:
                logger.debug(f"Tool {schema.name} completed.")
            else:
                logger.debug(f"Tool {schema.name} returned {result}")

            return result

        async def _on_invoke_tool(ctx: RunContextWrapper[Any], input: str) -> Any:
            try:
                return await _on_invoke_tool_impl(ctx, input)
            except Exception as e:
                if failure_error_function is None:
                    raise

                result = failure_error_function(ctx, e)
                if inspect.isawaitable(result):
                    return await result

                _error_tracing.attach_error_to_current_span(
                    SpanError(
                        message="Error running tool (non-fatal)",
                        data={
                            "tool_name": schema.name,
                            "error": str(e),
                        },
                    )
                )
                return result

        return FunctionTool(
            name=schema.name,
            description=schema.description or "",
            params_json_schema=schema.params_json_schema,
            on_invoke_tool=_on_invoke_tool,
            strict_json_schema=strict_mode,
        )

    # If func is actually a callable, we were used as @function_tool with no parentheses
    if callable(func):
        return _create_function_tool(func)

    # Otherwise, we were used as @function_tool(...), so return a decorator
    def decorator(real_func: ToolFunction[...]) -> FunctionTool:
        return _create_function_tool(real_func)

    return decorator