MCP server with OAuth 2.0 authorization provider running on Cloudflare Workers, demonstrating remote MCP authentication and authorization flows
Single tool 'add' has a clear verb-noun name and basic schema with typed parameters. However, the description is extremely minimal (23 chars), barely meeting the 10-char floor but well below the 194-char baseline for production tools. Parameter descriptions are present but terse (12-13 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 composition context. The tool is trivial (arithmetic) and lacks the depth expected of production-grade definitions.
Adds two numbers together
Tool description is 23 characters, below the 194-char baseline and lacks context on when/why to use it. Descriptions should state WHAT, WHEN, and any prerequisites.
Output schema is not documented in tool metadata. LLMs cannot plan downstream calls or extract fields without knowing the response structure.
Parameter descriptions are terse (12-13 chars). Should explain format, range, and constraints. E.g. 'First number to add (integer or float)' instead of 'First number to add'.
No error handling guidance. If inputs are invalid (NaN, infinity, non-numeric), the tool should return actionable error messages, not stack traces.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |
Tool is trivial and lacks composition context. A real MCP server should expose multiple tools that chain together. Single arithmetic tool does not demonstrate production readiness.