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 (23 chars), barely meeting the 10-char floor but well below the 50-200 char LLM-optimized baseline. Parameter descriptions are present but terse (12-18 chars each). No output schema is documented, the response structure is inferred from code (text content array) but not declared in tool metadata. No error handling guidance, no idempotency hints, no composition context. The tool is trivial (arithmetic) so gaps are less critical, but the pattern of minimal documentation would fail code review on a production server.
Adds two numbers together
Tool description is 23 characters, below LLM-optimized baseline of 50-200 chars. 'Adds two numbers together' lacks context on when to use this tool, what it returns, or any prerequisites.
Output schema is not documented in tool metadata. Response structure (text content array) is inferred from code, not declared. LLMs cannot plan downstream calls or extract fields without explicit schema documentation.
Parameter descriptions are terse (12-18 chars). 'First number to add' and 'Second number to add' lack format hints, range constraints, or type clarification. Descriptions should be 50-100 chars for clarity.
No error handling guidance. What happens if inputs are NaN, Infinity, or non-numeric? No recovery hints for the LLM.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 59 | 2026-07-28+ | v2 |
Tool is read-only (arithmetic) but no idempotentHint annotation present. Marking tools with idempotent/readOnly hints enables agents to safely retry without side-effect concerns.