An MCP server running on Cloudflare Workers with FastAPI/Starlette using Python via Pyodide, demonstrating tools, resources, and prompts
Two tools present with minimal but adequate naming and descriptions. Input schemas are well-formed with proper types and param descriptions. However, output schemas are undocumented, error handling is absent, and tool descriptions lack context about when/why to use them. The tools are simple arithmetic/calculation operations with no composition or chaining considerations. No security, pagination, or result-limiting concerns apply to this demo, but the lack of output schema documentation and error recovery guidance are significant gaps for production use.
Add two numbers
Calculate BMI given weight in kg and height in meters
Tool descriptions lack context and guidance. 'Add two numbers' and 'Calculate BMI given weight in kg and height in meters' are bare statements of what the tool does, not LLM-optimized descriptions. Missing: when to use (vs alternatives), what it returns, any prerequisites or constraints.
Output schemas are not documented. The source code shows tool registration but no explicit schema definition for return values. LLMs cannot infer what fields to expect from the response or plan downstream calls. Required for A/B-tier tools.
No error handling or recovery guidance. Tools lack explicit error classification (retryable, user-fixable, fatal) and actionable error messages. If a call fails, the LLM has no guidance on what to do next.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | D | 50 | <=2025-11-25 | v2 |
| 2026-03-09 | F | 43 | - | v1 |
Tool naming lacks strong action verbs. 'add' and 'calculate_bmi' are acceptable but non-standard in production baselines (avg best practice: get_, list_, create_, update_, delete_, search_, send_). 'add_numbers' and 'compute_bmi' would be more explicit.