MCP server that provides weather alerts and forecasts using the National Weather Service API
Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Both tools have action-verb names (get-alerts, get-forecast) and non-empty descriptions (18-32 chars, below the 50-200 char LLM-optimized baseline). Input parameters have type constraints (min/max for coordinates, length for state code) but lack detailed descriptions explaining format, prerequisites, or error recovery. Output schemas are not documented, LLMs cannot predict response structure. Error handling returns plain text without actionable guidance. No tool annotations (readOnlyHint, idempotentHint). Composition is sound (each tool does one thing), but parameter descriptions are minimal.
Get weather alerts for a state
Get weather forecast for a location
Parameter descriptions are minimal (1-2 words). 'Two-letter state code (e.g. CA, NY)' for state param is adequate, but latitude/longitude descriptions lack guidance on precision, valid ranges, or what happens for unsupported locations.
Output schemas are not documented. LLMs cannot predict the structure of alert or forecast responses. Responses return text content only, but no schema definition tells the LLM what fields to expect or how to chain to downstream tools.
Error messages lack actionable recovery guidance. 'Failed to retrieve alerts data' and 'This location may not be supported by the NWS API' are informative but do not tell the LLM what to do next (retry, ask user, try different coordinates).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Tool descriptions are too short (18-32 chars). Baseline for LLM-optimized descriptions is 50-200 chars. Current descriptions lack context on when to use each tool, prerequisites, or what the response contains.
No tool annotations (readOnlyHint, idempotentHint). Both tools are read-only and idempotent, but this is not declared in the tool definition. LLMs cannot infer safety properties without explicit hints.