No support of inputSchema in mcp.tool decorator

[fmtsvetkov]

Describe the bug
It's more an inconsistence than a bug but there is no "inputSchema" field in mcp.tool decorator while it's available in Tool

To Reproduce
@mcp.tool(
name="Name",
description=(
"description"
),
inputSchema = {}
)

Expected behavior
Add of mcp tool to mcp server

Current behavior
TypeError: FastMCP.tool() got an unexpected keyword argument 'inputSchema'

[ivanbelenky]

The actual inputSchema is missing based on the fact that there are 2 types of Tool obejcts, the internal server implementation and the protocol one usually imported as MCPTool. Have you chekced both tools structures?

in fastmcp.tools.base

class Tool(BaseModel):
    """Internal tool registration info."""

    fn: Callable[..., Any] = Field(exclude=True)
    name: str = Field(description="Name of the tool")
    description: str = Field(description="Description of what the tool does")
    parameters: dict[str, Any] = Field(description="JSON schema for tool parameters")
    fn_metadata: FuncMetadata = Field(
        description="Metadata about the function including a pydantic model for tool"
        " arguments"
    )
    is_async: bool = Field(description="Whether the tool is async")
    context_kwarg: str | None = Field(
        None, description="Name of the kwarg that should receive context"
    )
    annotations: ToolAnnotations | None = Field(
        None, description="Optional annotations for the tool"
    )

in types

# types.py
class Tool(BaseModel):
    """Definition for a tool the client can call."""

    name: str
    """The name of the tool."""
    description: str | None = None
    """A human-readable description of the tool."""
    inputSchema: dict[str, Any]
    """A JSON Schema object defining the expected parameters for the tool."""
    annotations: ToolAnnotations | None = None
    """Optional additional tool information."""
    model_config = ConfigDict(extra="allow")

I know nothing about nothing but allowing for inputSchema would require extra validation with respect to the automatically introspective build of parameters that precisely holds that info.