MCP server providing weather alerts and forecast data from the National Weather Service API
Server has 4 tools with basic descriptions and input schemas, but significant quality gaps. Tool naming is acceptable (verb_noun pattern), but descriptions are minimal (10-50 chars, well below the 194-char baseline). Input schemas present but lack depth: no enums for constrained values (e.g., state codes), no min/max bounds on numeric parameters, no output schemas documented. Error handling is minimal, tools return plain strings with no recovery guidance. Duplicate tool registration (get_alerts appears twice) suggests incomplete implementation. No tool annotations, no pagination support, no structured output. Resources feature is enabled but not used in tool definitions.
Echo a message as a resource
Get weather alerts for a US state.
Get weather alerts for a US state.
Get weather forecast for a location.
Descriptions are too short (10-50 chars vs. 194-char baseline). 'Get weather alerts for a US state' lacks context on when to use this tool, what it returns, or prerequisites.
No output schemas documented. LLMs cannot plan downstream calls or extract structured data. Tools return plain strings; no field definitions for parsed results.
Input parameters lack constraints. 'state' parameter accepts any string; should be an enum of valid US state codes (CA, NY, TX, etc.). 'latitude' and 'longitude' lack min/max bounds.
Error handling returns plain strings with no recovery guidance. 'Unable to fetch alerts' tells the LLM nothing about retry eligibility, user-fixable issues, or next steps.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | 2026-07-28+ | v2 |
Duplicate tool registration: get_alerts appears in both mcpserver/client-sse.py and mcpserver/server.py. This suggests incomplete refactoring or tool discovery issues.