Two tools with basic schemas and minimal descriptions. Both tools have input schemas with proper types (number, string, enum), but descriptions are extremely short (10-50 chars) and lack context for LLM selection. No output schema documentation. Error handling is minimal (divide-by-zero check in 'calculate' returns text, not structured error). No parameter descriptions beyond type hints. Tool names are generic ('add', 'calculate') without clear verb-noun patterns. Schemas are present but descriptions fall well below the 50-200 char baseline for A-grade tools.

• Expand tool descriptions to 80-150 chars. Example for 'add': 'Adds two numbers and returns their sum. Use this for simple addition; use calculate() for subtract, multiply, or divide operations.'
• Add parameter descriptions. For 'a' and 'b': 'A number to add (any real number, positive or negative)'. For 'operation': 'The arithmetic operation: add (sum), subtract (difference), multiply (product), or divide (quotient).'
• Document output schema in tool metadata or description. Example: 'Returns {content: [{type: "text", text: "<result>"}]} where result is a number or error message.'
• Refactor error handling to return structured errors. Instead of plain text, return {content: [{type: 'text', text: 'Error: division by zero'}], isError: true} or use MCP error response format.
• Rename tools to verb_noun pattern: 'add' → 'add_numbers', 'calculate' → 'perform_arithmetic'. This clarifies intent and helps LLMs distinguish from other tools.