MCP server with OAuth authentication and a simple arithmetic tool
Single tool 'add' with critical definition gaps. Tool description is missing entirely (null in source). No output schema documented. No error handling guidance. Naming is acceptable (verb_noun: 'add') but insufficient to overcome missing descriptions and documentation.
Tool 'add' has no description. LLMs cannot determine when or why to select this tool without a description explaining its purpose, when to use it, and what it returns.
All input parameters (a, b) have null descriptions. Parameter descriptions are mandatory, LLMs cannot infer that 'a' and 'b' are operands for addition.
No output schema documented. Tool returns {content: [{type: 'text', text: string}]} but this structure is not declared in the tool definition. LLMs cannot plan downstream operations without knowing the response shape.
No error handling or recovery guidance. If inputs are invalid (non-numeric), the tool will fail silently. No error message tells the LLM what went wrong or how to retry.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2026-07-28+ | v2 |
Tool is trivial (bare arithmetic) and does not demonstrate real-world agent patterns. No pagination, no resource chaining, no idempotency considerations. This is a proof-of-concept, not production-ready.