Five tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. All tools have descriptions (10-50 chars, below the 50-200 char baseline for LLM optimization). Input schemas present but sparse: calculate and reverse_string lack parameter descriptions; finance tools have better coverage but missing output schema documentation. No error handling guidance, no tool annotations, no idempotency hints. Tools are read-only and simple, but descriptions are too terse to guide LLM selection effectively.

• Expand tool descriptions to 50-200 chars. Example: 'calculate' → 'Perform arithmetic operations (add, subtract, multiply, divide) on two numbers. Returns the result as a string. Use for math-heavy workflows.'
• Add parameter descriptions to all tools. For 'operation' in calculate: 'One of: add, subtract, multiply, divide. Case-sensitive.'
• Document output schemas explicitly. For fetch_stock_history: 'Returns JSON with fields: ticker (string), period (string), interval (string), row_count (int), latest (object with date, open, high, low, close, volume), history (array of OHLCV objects).'
• Implement structured error responses. Instead of returning error strings, return JSON: {"error": "divide_by_zero", "message": "Cannot divide by zero", "recovery": "Check that b is not zero."}
• Add tool annotations via FastMCP. Mark all tools with readOnlyHint=true since they only fetch data and never modify state.