Improving how function docstring gets converted to tool's jsonschema for FastMCP

Comece em src/mcp/server/fastmcp/tools/base.py e src/mcp/server/fastmcp/utilities/func_metadata.py e, em seguida, revise o utilitário Goose vinculado e os exemplos de testes. Primeiro determine qual estilo de docstring e qual dependência de parser são aceitáveis. Considera-se concluído quando as descrições compatíveis de argumentos e funções aparecem no esquema JSON gerado, com testes cobrindo o estilo escolhido.

Is your feature request related to a problem? Please describe.
Tool descriptions are not parsed as expected from the function docstring when using FastMCP. This affects tool calling performance.

Currently, FastMCP does some function inspection to create the docstring here:

• https://github.com/modelcontextprotocol/python-sdk/blob/775f87981300660ee957b63c2a14b448ab9c3675/src/mcp/server/fastmcp/tools/base.py#L55-L59
• https://github.com/modelcontextprotocol/python-sdk/blob/775f87981300660ee957b63c2a14b448ab9c3675/src/mcp/server/fastmcp/utilities/func_metadata.py#L105-L174

From my understanding, it creates a FuncMetadata model in pydantic which then gets converted to jsonschema.

Current behaviour:
If we have a tool such as:

def add_numbers(a: float, b: float) -> float:
    """
    Adds two numbers and returns the result.

    Args:
        a (float): The first number.
        b (float): The second number.

    Returns:
        float: The sum of a and b.
    """
    return a + b

it gets parsed into:

>>> func_arg_metadata = func_metadata(add_numbers)
>>> parameters = func_arg_metadata.arg_model.model_json_schema()
>>> parameters
{'properties': {'a': {'title': 'A', 'type': 'number'}, 'b': {'title': 'B', 'type': 'number'}}, 'required': ['a', 'b'], 'title': 'add_numbersArguments', 'type': 'object'}

>>> add_numbers.__doc__  
'\nAdds two numbers and returns the result.\n\nArgs:\n    a (float): The first number.\n    b (float): The second number.\n\nReturns:\n    float: The sum of a and b.\n'

Describe the solution you'd like
It'd be nicer to follow one of the python docstring styles and parse out the argument descriptions from the docstring.

{
  "name": "add_numbers",
  "description": "Adds two numbers and returns the sum.",
  "parameters": {
    "type": "object",
    "properties": {
      "a": {
        "type": "number",
        "description": "The first number to add."
      },
      "b": {
        "type": "number",
        "description": "The second number to add."
      }
    },
    "required": ["a", "b"]
  }
}

Describe alternatives you've considered
we used to do this in a previous python version of goose: https://github.com/block/goose/blob/eccb1b22614f39b751db4e5efd73d728d9ca40fc/packages/exchange/src/exchange/utils.py#L82-L107

here are some test examples: https://github.com/block/goose/blob/eccb1b22614f39b751db4e5efd73d728d9ca40fc/packages/exchange/tests/test_utils.py#L32-L136

Additional context
I am happy to add this in - wanted to post this first to check that you're okay with enforcing a docstring style ("google", "numpy", "sphinx") & adding griffe as a dependency.