Weather information server providing alerts and forecasts from the National Weather Service
Two tools with basic verb-noun naming (get_alerts, get_forecast). Both have short descriptions (40-50 chars) and documented input schemas with types. However, descriptions lack context on WHEN to use each tool, prerequisites, or what the output contains. No output schema documentation. Parameters have types and brief descriptions but lack constraints (e.g., state code format, lat/lon ranges). Error handling returns plain strings with no recovery guidance. No pagination, no structured output, no tool annotations.
Get weather alerts for a US state.
Get weather forecast for a location.
Descriptions are too brief (40-50 chars) and lack context. No explanation of WHEN to use each tool, what output format to expect, or dependencies between tools.
No output schema documented. Tools return plain strings; LLMs cannot parse structured data or chain results to other tools. Baseline: 100% of A+ tools document return types.
Parameters lack constraints and format guidance. 'state' has no enum or pattern (should be 2-letter code); latitude/longitude lack min/max bounds. Baseline: constrained inputs prevent hallucinated values.
Error handling returns generic strings ('Unable to fetch alerts') with no recovery guidance. LLMs cannot determine if the error is retryable, user-fixable, or fatal.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Both tools are read-only but this is not declared in the schema, forcing LLMs to infer safety.