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 schema documentation. 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 for 'add': 'Adds two numbers and returns their sum. Use this for simple arithmetic addition. Returns a numeric result as text.'
• Add parameter descriptions in Zod schema or via server metadata. Example: 'a: First number to add (any real number)', 'b: Second number to add (any real number)', 'operation: Arithmetic operation to perform (add, subtract, multiply, or divide)'.
• Document output schema explicitly. Example: 'Returns {content: [{type: "text", text: "<numeric result>"}]}. For divide by zero, returns error message instead.'
• Rename tools to action verbs: 'add' → 'perform_addition', 'calculate' → 'perform_arithmetic_operation'. This helps LLMs infer intent from the name alone.
• Implement structured error responses. For divide-by-zero, return {content: [{type: 'text', text: 'Error: division by zero. Divisor (b) must be non-zero.'}]} with a clear, actionable message.