An MCP server deployed on Cloudflare Workers that provides OAuth 2.0 authorization and remote MCP tool access with a web-based authorization interface
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. Parameter descriptions are present but terse (12-18 chars each). No output schema is documented, the response structure is inferred from code only. No error handling guidance, no idempotency hints, no composition context. The tool is trivial (arithmetic) and lacks production-grade polish. Baseline: A+ tools average 194 chars for descriptions and 72 chars per param; this server is 1/8th that depth.
Adds two numbers together
Tool description is 23 characters, below production baseline of 194 chars. Lacks context on when to use, what it returns, and any prerequisites.
Output schema not documented. Response structure (content array with text type) is visible only in code, not in tool metadata. LLMs cannot plan downstream calls without knowing return fields.
Parameter descriptions are terse (12 - 18 chars). 'First number to add' and 'Second number to add' are minimal; no mention of valid ranges, precision, or edge cases (e.g., does it handle Infinity, NaN, very large numbers?).
No error handling guidance. What happens if inputs are null, undefined, or non-numeric? No recovery hints for the LLM.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
Tool is trivial (arithmetic only). Real MCP servers should expose meaningful domain operations. This demo lacks composition, state management, or integration patterns.