MCP server with OAuth 2.0 authorization provider running on Cloudflare Workers, demonstrating remote authentication flows
Single tool 'add' has a clear verb-noun name and basic schema with typed parameters. However, the description is extremely minimal (22 chars), barely meeting the 10-char floor. Parameter descriptions are present but terse (12-18 chars each). No output schema is documented, the response structure is inferred from code but not declared in tool metadata. No error handling guidance, no idempotency hints, no security considerations. The tool is trivial (arithmetic), so complexity is low, but the definition lacks the rigor expected of production tools. Baseline: 194 chars avg description, 72 chars avg param annotation, this server is 1/9th the expected description length.
Adds two numbers together
Tool description is 22 characters, far below the 194-char baseline for production tools. 'Adds two numbers together' lacks context on when to use it, what it returns, or any prerequisites.
Output schema is not documented in tool metadata. Response structure (content array with text field) is visible in code but not declared in the tool definition, forcing LLMs to infer the shape.
Parameter descriptions are minimal (12 - 18 chars). 'First number to add' and 'Second number to add' lack format hints, range constraints, or examples. Baseline is 72 chars per param.
No error handling guidance. If inputs are non-numeric or NaN, the tool provides no recovery hint. LLMs cannot self-correct without actionable error messages.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |
Tool lacks idempotency hint. Arithmetic is naturally idempotent, but this is not declared via toolAnnotations (idempotentHint), leaving LLMs uncertain about retry safety.