FyAgent exposes 4 tools with critical definition gaps. Tool names lack clear action verbs (get_tool_versions is acceptable, but run_tool_lifecycle_action is vague). Descriptions are present but minimal (10-80 chars, below the 50-200 char LLM-optimized baseline). Input schemas are visible but lack parameter descriptions, the 'tools' array parameter has a description, but 'action' in run_tool_lifecycle_action lacks clarity on valid values. No output schemas documented. Error handling is absent. The tools appear to be Tauri command wrappers, not MCP-native definitions, tool registration is inferred from file paths, not explicit MCP schema declarations visible in source.

• Document output schemas for all tools. Example for get_tool_versions: {"tools": [{"name": string, "version": string, "installed": boolean}], "total": number}
• Convert 'action' parameter to an enum in the schema: {"type": "string", "enum": ["install", "install_official_npm", "install_native", "update"]} instead of free-text description.
• Expand tool descriptions to 100-150 chars. Example: 'Get installed versions of specified tools. Returns version strings and installation status. Call this before update_tool to check current versions.'
• Split run_tool_lifecycle_action into separate tools: install_tool(tools: string[]) and update_tool(tools: string[]) for clarity and single responsibility.
• Add error handling guidance to descriptions. Example: 'If a tool is not found, returns error code TOOL_NOT_FOUND. Call get_available_tools() to list valid tool names.'