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). Tool names lack action verbs ('add' and 'calculate' are weak; 'perform_addition' and 'perform_calculation' would be clearer). No parameter descriptions beyond type hints. Schemas are present but sparse.

• Expand tool descriptions to 50-200 chars. Example: 'add' → 'Adds two numbers and returns their sum. Use when you need basic arithmetic addition. Returns a single numeric result.'
• Add parameter descriptions in Zod schema via .describe(). Example: z.number().describe('First operand (any real number)'). This makes descriptions visible to LLMs without parsing JSON Schema.
• Document output schema in tool description. Example: 'Returns {content: [{type: "text", text: "<numeric result>"}]}'.
• Rename tools with action verbs: 'add' → 'perform_addition', 'calculate' → 'perform_arithmetic_operation'.
• Implement structured error responses. Return {content: [{type: 'text', text: 'Error: Division by zero. Use a non-zero divisor.'}]} or a dedicated error field with code and recovery hints.