A demonstration MCP server that provides weather alerts and forecast tools using the National Weather Service API
Two tools with basic but incomplete definitions. Both have action-verb names (get_alerts, get_forecast) and descriptions present, but descriptions are brief (under 100 chars) and lack context on when to use each tool or what they return. Input schemas are present with proper types and descriptions for parameters. However, output schemas are completely undocumented, LLMs cannot predict what fields to expect from responses. No error handling guidance, no pagination support despite potentially large result sets, and no indication of output structure. Naming is clear but descriptions fall short of production baseline (194 chars average for A+ tools).
Get weather alerts for a US state.
Get weather forecast for a location.
Output schemas completely undocumented. LLMs cannot predict response structure, fields, or data types. Both tools return formatted strings with no schema definition.
Tool descriptions are too brief (under 100 chars) and lack context. Missing: when to use each tool, what distinguishes them, what data they return, and any prerequisites or dependencies.
No error handling guidance. Tools can fail (API timeouts, invalid coordinates, missing state) but return no actionable recovery hints. LLM cannot self-correct on failure.
No pagination or result limits documented. get_alerts could return hundreds of active alerts; no limit, offset, or pagination parameters offered. Large responses waste tokens and degrade LLM reasoning.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
Parameter descriptions lack format constraints. 'state' accepts 'Two-letter US state code' but no enum of valid codes; 'latitude'/'longitude' lack range constraints (±90, ±180). LLMs may pass invalid values.