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 text, not structured error). No parameter descriptions beyond type hints. Tool names lack action verbs ('add' and 'calculate' are weak; 'perform_addition' and 'perform_calculation' would be clearer). No tool annotations (readOnlyHint, idempotentHint). Composition is reasonable (two separate tools), but descriptions do not guide LLM selection or explain when to use each.

• Expand tool descriptions to 50-200 chars. Example for 'add': 'Adds two numbers and returns the sum. Use this for simple addition when you only need to add two values. Returns a numeric result.'
• 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)'. For 'calculate', describe 'operation: The arithmetic operation to perform (add, subtract, multiply, or divide)'.
• Document output schema explicitly. Both tools return {content: [{type: 'text', text: string}]}. Specify this in tool metadata or response documentation.
• Rename tools to action verbs: 'add' → 'add_numbers', 'calculate' → 'perform_arithmetic'. This makes intent clear without reading descriptions.
• Improve error handling in 'calculate'. For divide-by-zero, return a structured error like {error: 'division_by_zero', message: 'Cannot divide by zero. Check your inputs and retry.', retryable: false} instead of plain text.