Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and output structure. Both tools have verb-noun naming (get-alerts, get-forecast) and descriptions present, but descriptions are minimal (18-28 chars, well below the 50-200 char LLM-optimized baseline). Parameter descriptions exist but lack detail on constraints, formats, and error recovery. No documented output schemas. Error handling returns plain text without actionable guidance for LLM retry logic.

• Expand tool descriptions to 80-150 chars. Example: 'get-alerts' → 'Retrieve active weather alerts for a US state. Returns event type, severity, area affected, and headline. Useful for checking current warnings before planning travel or outdoor activities.'
• Document output schemas explicitly. Define that get-alerts returns {alerts: [{event, area, severity, status, headline}], count: number} and get-forecast returns {location: {lat, lon}, periods: [{name, temperature, windSpeed, forecast}]}.
• Add actionable error messages. Replace 'Failed to retrieve forecast data' with 'Forecast unavailable for coordinates {lat},{lon}. NWS API only supports US locations. Verify coordinates are within continental US, Alaska, or Hawaii.'
• Add constraint details to parameter descriptions. For state: 'Two-letter US state code (e.g., CA, NY, TX). Must be uppercase or will be converted.' For coordinates: 'Latitude and longitude in decimal degrees. Must be within US boundaries (NWS API limitation).'
• Add limit and pagination support. Include optional 'limit' parameter (default 20, max 100) for alerts and forecast periods. Return total_count and next_cursor in responses to enable multi-page retrieval.