Function●Since v0.2

tool

Convert Python functions and Runnables to LangChain tools.

Can be used as a decorator with or without arguments to create tools from functions.

Functions can have any signature - the tool will automatically infer input schemas unless disabled.

Requirements

Functions should have type hints for proper schema inference.
Functions may accept multiple arguments and return types are flexible; outputs will be serialized if needed.
When using with Runnable, a string name must be provided.

tool(
  name_or_callable: str | Callable | None = None,
  runnable: Runnable | None = None,
  *args: Any = (),
  description: str | None = None,
  return_direct: bool = False,
  args_schema: ArgsSchema | None = None,
  infer_schema: bool = True,
  response_format: Literal['content', 'content_and_artifact'] = 'content',
  parse_docstring: bool = False,
  error_on_invalid_docstring: bool = True,
  extras: dict[str, Any] | None = None
) -> BaseTool | Callable[[Callable | Runnable], BaseTool]

Parameters

Name	Type	Description
`name_or_callable`	`str \| Callable \| None`	Default:`None` Optional name of the tool or the `Callable` to be converted to a tool. Overrides the function's name. Must be provided as a positional argument.
`runnable`	`Runnable \| None`	Default:`None` Optional `Runnable` to convert to a tool. Must be provided as a positional argument.
`description`	`str \| None`	Default:`None` Optional description for the tool. Precedence for the tool description value is as follows: This `description` argument (used even if docstring and/or `args_schema` are provided) Tool function docstring (used even if `args_schema` is provided) `args_schema` description (used only if `description` and docstring are not provided)
`*args`	`Any`	Default:`()` Extra positional arguments. Must be empty.
`return_direct`	`bool`	Default:`False` Whether to return directly from the tool rather than continuing the agent loop.
`args_schema`	`ArgsSchema \| None`	Default:`None` Optional argument schema for user to specify.
`infer_schema`	`bool`	Default:`True` Whether to infer the schema of the arguments from the function's signature. This also makes the resultant tool accept a dictionary input to its `run()` function.
`response_format`	`Literal['content', 'content_and_artifact']`	Default:`'content'` The tool response format. If `'content'`, then the output of the tool is interpreted as the contents of a `ToolMessage`. If `'content_and_artifact'`, then the output is expected to be a two-tuple corresponding to the `(content, artifact)` of a `ToolMessage`.
`parse_docstring`	`bool`	Default:`False` If `infer_schema` and `parse_docstring`, will attempt to parse parameter descriptions from Google Style function docstrings.
`error_on_invalid_docstring`	`bool`	Default:`True` If `parse_docstring` is provided, configure whether to raise `ValueError` on invalid Google Style docstrings.
`extras`	`dict[str, Any] \| None`	Default:`None` Optional provider-specific extra fields for the tool. Used to pass configuration that doesn't fit into standard tool fields. Chat models should process known extras when constructing model payloads. Example For example, Anthropic-specific fields like `cache_control`, `defer_loading`, or `input_examples`.

View source on GitHub

tool

Convert Python functions and Runnables to LangChain tools.

Can be used as a decorator with or without arguments to create tools from functions.

Functions can have any signature - the tool will automatically infer input schemas unless disabled.

Requirements

Functions should have type hints for proper schema inference.
Functions may accept multiple arguments and return types are flexible; outputs will be serialized if needed.
When using with Runnable, a string name must be provided.

tool( name_or_callable: str | Callable | None = None, runnable: Runnable | None = None, *args: Any = (), description: str | None = None, return_direct: bool = False, args_schema: ArgsSchema | None = None, infer_schema: bool = True, response_format: Literal['content', 'content_and_artifact'] = 'content', parse_docstring: bool = False, error_on_invalid_docstring: bool = True, extras: dict[str, Any] | None = None ) -> BaseTool | Callable[[Callable | Runnable], BaseTool]

Parameters

Name	Type	Description
`name_or_callable`	`str \| Callable \| None`	Default:`None` Optional name of the tool or the `Callable` to be converted to a tool. Overrides the function's name. Must be provided as a positional argument.
`runnable`	`Runnable \| None`	Default:`None` Optional `Runnable` to convert to a tool. Must be provided as a positional argument.
`description`	`str \| None`	Default:`None` Optional description for the tool. Precedence for the tool description value is as follows: This `description` argument (used even if docstring and/or `args_schema` are provided) Tool function docstring (used even if `args_schema` is provided) `args_schema` description (used only if `description` and docstring are not provided)
`*args`	`Any`	Default:`()` Extra positional arguments. Must be empty.
`return_direct`	`bool`	Default:`False` Whether to return directly from the tool rather than continuing the agent loop.
`args_schema`	`ArgsSchema \| None`	Default:`None` Optional argument schema for user to specify.
`infer_schema`	`bool`	Default:`True` Whether to infer the schema of the arguments from the function's signature. This also makes the resultant tool accept a dictionary input to its `run()` function.
`response_format`	`Literal['content', 'content_and_artifact']`	Default:`'content'` The tool response format. If `'content'`, then the output of the tool is interpreted as the contents of a `ToolMessage`. If `'content_and_artifact'`, then the output is expected to be a two-tuple corresponding to the `(content, artifact)` of a `ToolMessage`.
`parse_docstring`	`bool`	Default:`False` If `infer_schema` and `parse_docstring`, will attempt to parse parameter descriptions from Google Style function docstrings.
`error_on_invalid_docstring`	`bool`	Default:`True` If `parse_docstring` is provided, configure whether to raise `ValueError` on invalid Google Style docstrings.
`extras`	`dict[str, Any] \| None`	Default:`None` Optional provider-specific extra fields for the tool. Used to pass configuration that doesn't fit into standard tool fields. Chat models should process known extras when constructing model payloads. Example For example, Anthropic-specific fields like `cache_control`, `defer_loading`, or `input_examples`.

tool

Parameters

LangChain Assistant

Menu

tool

Parameters

tool

Used in Docs

Parameters

Menu

tool

Used in Docs

Parameters