Serverless MCP server running on AWS Lambda with Middy middleware
Single tool 'add' has critical definition gaps. Tool name lacks action verb (should be 'compute_sum' or 'add_numbers'). No tool description provided. Input schema uses Zod but lacks explicit type/description metadata visible in source. Output schema not documented. No error handling guidance. Fails multiple hard scoring rules.
Parameters 'a' and 'b' have null descriptions (visible in Input schema).
Tool name 'add' does not start with an action verb. Should be 'compute_sum', 'add_numbers', or similar. LLMs rely on verb-noun naming to infer intent.
Output schema not documented. LLMs need to know what fields to expect (e.g., does it return {result: number} or {sum: number, input_a: number, input_b: number}?).
No error handling guidance. If inputs are invalid (non-numeric), the tool should return a clear, actionable error message, not a 500 error.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 30 | 2026-07-28+ | v2 |