Two tools with basic schemas and minimal descriptions. Both tools have input schemas with proper types (number, string enum), but descriptions are extremely short (10-40 chars), falling well below the 50-200 char baseline for LLM-optimized descriptions. No output schemas documented. Error handling is minimal (divide-by-zero check in 'calculate' returns plain text, not structured error guidance). Tool names lack action verbs ('add' and 'calculate' are weak; 'perform_addition' and 'perform_calculation' would be clearer). No parameter descriptions beyond type hints. No tool annotations (readOnlyHint, idempotentHint). Composition is reasonable (two separate tools), but descriptions do not explain WHEN to use each tool or what distinguishes them.

• Expand tool descriptions to 50-200 chars. Example for 'add': 'Adds two numbers and returns the sum. Use this for simple addition; use calculate() for subtract, multiply, or divide operations.'
• Add descriptions to all parameters. Example: 'a: The first number to add (any real number)' and 'b: The second number to add (any real number)'.
• Document output schema in tool metadata. Both tools return {content: [{type: 'text', text: string}]}. Declare this explicitly so LLMs know the response structure.
• Rename tools with action verbs: 'add' → 'perform_addition', 'calculate' → 'perform_arithmetic'. This helps LLMs disambiguate intent.
• Improve error handling in 'calculate'. Return structured error: {error: 'division_by_zero', message: 'Cannot divide by zero. Check your inputs and retry.', retryable: true} instead of plain text.