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 tool only). Tool names are action-oriented (add, calculate) but descriptions don't explain WHEN to use each tool or their differences. No parameter descriptions beyond type hints in schema. Lacks guidance on tool composition or error recovery.

• Expand tool descriptions to 50-200 chars. For 'add': 'Adds two numbers and returns the sum. Use this for simple addition; use calculate() for subtract, multiply, or divide.' For 'calculate': 'Performs arithmetic operations (add, subtract, multiply, divide) on two operands. Returns numeric result or error if division by zero.'
• Add parameter descriptions in schema. E.g., 'a': {'type': 'number', 'description': 'First operand (any real number)'}, 'b': {'type': 'number', 'description': 'Second operand (any real number)'}, 'operation': {'type': 'string', 'enum': [...], 'description': 'Arithmetic operation: add, subtract, multiply, or divide.'}
• Document output schema. Define return type as {type: 'object', properties: {result: {type: 'number', description: 'Numeric result of the operation'}, error?: {type: 'string', description: 'Error message if operation failed'}}}
• Improve error handling. Return structured errors with actionable guidance: {error: 'Division by zero', suggestion: 'Divisor (b) must be non-zero. Try a different value.'} instead of plain text.
• Consolidate tools. Remove 'add' tool (redundant with calculate operation='add') or clearly document when each is preferred. Reduces LLM confusion and token waste.