A remote MCP server providing calculator tools without authentication, deployed on Cloudflare Workers
Two tools with minimal descriptions and basic schemas. 'add' (9 chars) and 'calculate' (10 chars) descriptions are far below the 50-200 char baseline for LLM-optimized tools. Both tools lack output schema documentation. Parameter descriptions are present but generic. No error handling guidance, no idempotency hints, no recovery paths. Tool composition is reasonable (add vs calculate separation), but descriptions do not explain WHEN to use each tool or what distinguishes them.
Simple addition tool
Calculator tool with multiple operations
Tool descriptions are critically short (9-10 chars). Current descriptions lack context on WHEN to use each tool and what distinguishes 'add' from 'calculate'.
No output schema documented. LLMs cannot plan downstream calls or extract return values without knowing the response structure. Both tools return text content but this is not formally specified.
No error handling guidance. 'calculate' handles divide-by-zero with a text error message, but LLM cannot determine if error is retryable, user-fixable, or fatal. No recovery path suggested.
Parameter descriptions are generic. 'First number to add' and 'First operand' do not specify format, range, or constraints. No guidance on valid numeric ranges or precision expectations.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, idempotentHint). Both tools are read-only and idempotent, but this is not declared in the schema. Agents cannot infer safety properties.