A remote MCP server providing calculator tools without authentication, deployed on Cloudflare Workers
Two tools with basic schemas and minimal descriptions. Both tools have proper input schemas with typed parameters and enums (calculate tool), but descriptions are extremely short (10-40 chars, well below the 50-200 char baseline for LLM-optimized descriptions). No output schema documentation. Error handling is minimal (divide-by-zero check in calculate tool only). Tool names lack action verbs ('add' and 'calculate' are weak; 'perform_addition' and 'perform_calculation' would be clearer). No parameter descriptions beyond type info. No composition guidance or chaining support.
Simple addition tool
Calculator tool with multiple operations
Tool descriptions are critically short (10-40 chars vs. 50-200 char baseline). 'Simple addition tool' and 'Calculator tool with multiple operations' lack context for LLM selection, WHEN to use each tool, and what they return.
Tool names lack action verbs. 'add' and 'calculate' are generic; LLMs cannot distinguish intent. Should be 'perform_addition' or 'add_numbers' and 'perform_arithmetic' or 'calculate_result'.
No parameter descriptions. Schema defines types (number, string, enum) but LLMs cannot infer meaning from names alone. 'a' and 'b' are ambiguous, are they operands, indices, or something else? 'operation' enum is clear but lacks guidance on when to use each operation.
No output schema documented. LLMs cannot plan downstream calls or extract results reliably. What fields does the response contain? Is it just a number, or a structured object with metadata?
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 40 | 2026-07-28+ | v2 |
Minimal error handling. Only divide-by-zero check in calculate tool; no guidance for LLM recovery. Error message 'Cannot divide by zero' is user-friendly but lacks actionable next steps for the agent.