Find agent skills by outcome

def validate_email(cls

v: str) -> str:

age: int = Field(...

description=User's age

Communication

email: str = Field(...

description=User's email address

idempotentHint: True

# Repeated calls have no additional effect

name: str = Field(...

description=User's full name

from pydantic import BaseModel

Field

destructiveHint: False

# Tool does not perform destructive operations

tags: Optional[List[str]] = Field(default_factory=list

description=List of tags to apply

readOnlyHint: True

# Tool does not modify environment

param2: Optional[int] = Field(default=None

description=Optional integer parameter with constraints

validate_assignment=True

# Validate on assignment

param1: str = Field(...

description=First parameter description (e.g.

str_strip_whitespace=True

# Auto-strip whitespace from strings

Use snake_case for tool names (e.g.

search_users

from pydantic import BaseModel

Field

Coding & Debugging

The official MCP Python SDK provides FastMCP

a high-level framework for building MCP servers. It provides:

- Examples: `github_mcp`

`jira_mcp`

**For complete SDK documentation

use WebFetch to load:**

from pydantic import BaseModel

Field

@mcp.tool(name=tool_name

annotations={...})

from typing import Optional

List

Coding & Debugging

This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup

tool registration patterns

- [ ] Error messages are clear

actionable

- [ ] Error handling uses proper type guards (e.g.

`axios.isAxiosError`