Two tools with minimal descriptions and basic schemas. 'add' (9 chars) and 'calculate' (9 chars) descriptions are far below the 10 - 1024 char baseline and provide no context for LLM selection. Parameter descriptions exist but are generic ('First number to add'). No output schema documented. No error handling guidance beyond a hardcoded divide-by-zero check. Tools lack verb-noun naming clarity (both are nouns/verbs but lack specificity). No tool annotations, no pagination, no recovery guidance.

• Expand tool descriptions to 50 - 150 chars. Example: 'add: Adds two numbers and returns the sum. Use when you need basic arithmetic. Accepts integers and decimals.' This tells LLMs what, when, and what to expect.
• Document output schema explicitly. Declare that both tools return {result: number} or {value: number, operation: string}. Include this in the tool definition or response documentation.
• Add parameter constraints to descriptions. Change 'First number to add' to 'First operand (integer or decimal, no limit)' or 'First operand (range: -1e10 to 1e10)'.
• Enhance error handling for divide-by-zero. Return structured error: {error: 'division_by_zero', message: 'Cannot divide by zero. Check the divisor (b parameter) and retry.', retryable: false}.
• Add tool annotations to schema. Mark both tools with readOnlyHint: true and idempotentHint: true so LLMs know they are safe to call multiple times without side effects.