MCP server for retrieving weather alerts and forecasts from the National Weather Service API
Two tools with basic verb-noun naming (get_alerts, get_forecast). Both have short descriptions (under 100 chars) and documented input schemas with type and description fields. However, output schemas are completely undocumented, tools return plain strings with no structured format guidance. Parameter descriptions are minimal (e.g., 'Two-letter US state code' lacks validation rules or error cases). No error handling guidance, no pagination support, no output field documentation. Schemas present but sparse; descriptions exist but fall short of LLM-optimization standards (50-200 chars recommended). No tool annotations (readOnlyHint, etc.) despite both being read-only operations.
Get weather alerts for a US state.
Get weather forecast for a location.
Output schemas completely undocumented. Both tools return plain strings with no structured format guidance. LLMs cannot plan downstream operations or extract specific fields.
Descriptions too brief and lack LLM-optimization. 'Get weather alerts for a US state' (45 chars) and 'Get weather forecast for a location' (36 chars) do not explain WHEN to use each tool, what data is returned, or how to interpret results.
No error handling guidance. Tools return 'Unable to fetch alerts or no alerts found' and 'Unable to fetch forecast data' with no recovery hints. LLM cannot determine if error is retryable, user-fixable, or fatal.
Parameter descriptions lack validation rules and constraints. 'Two-letter US state code (e.g. CA, NY)' does not specify format, range, or what happens if invalid input is passed. Latitude/longitude lack bounds or precision guidance.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
No tool annotations despite both tools being read-only. Missing readOnlyHint annotation prevents agents from understanding safety profile and retry semantics.