An MCP server deployed on Cloudflare Workers with OAuth 2.0 authentication support, demonstrating remote MCP server capabilities with a simple arithmetic tool
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 (18-19 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 production-grade polish expected of agent tools.
Adds two numbers together
Tool description is 23 characters, below the 50-char minimum for LLM clarity. 'Adds two numbers together' lacks context on when to use this tool, what it returns, or any prerequisites.
No output schema documented. The tool returns {content: [{type: 'text', text: string}]} but this structure is not declared in tool metadata. LLMs cannot plan downstream calls or validate responses.
Parameter descriptions are 18 - 19 characters each ('First number to add', 'Second number to add'). While present, they are minimal and do not specify constraints (e.g., range, precision, special values).
No error handling guidance. What happens if inputs are NaN, Infinity, or non-numeric? How should the LLM recover? No recovery hints provided.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Tool is marked READ_ONLY but serves no practical purpose in a real agent system. Single arithmetic operation does not demonstrate composition, chaining, or realistic use cases.