Two tools with basic verb-noun naming (get_alerts, get_forecast). Both have short descriptions (34-40 chars, below the 50-200 char baseline for LLM-optimized descriptions). Input schemas are present with typed parameters and descriptions. However, output schemas are completely undocumented, tools return plain strings with no structured format guidance. No error handling guidance, no pagination support, no output field documentation. Descriptions lack context on when to use each tool or what data structure is returned. Parameters are minimally described.

• Document output schemas explicitly. Define the structure of alert and forecast responses (e.g., list of objects with fields: event, area, severity, description for alerts; list of periods with name, temperature, wind, forecast for forecasts).
• Expand tool descriptions to 50-200 characters. Example: 'Get active weather alerts for a US state. Returns a list of current alerts with event type, affected area, severity level, and recommended actions.' Include when to use vs similar tools.
• Add error handling guidance. Return structured error responses like: '{"error": "Invalid state code", "hint": "Use 2-letter US state abbreviation (CA, NY, TX, etc.)"}' instead of plain strings.
• Add pagination to get_alerts. Include limit (default 20, max 100) and offset parameters. Return total_count and next_offset in response so LLMs can fetch additional alerts if needed.
• Replace example values with enum constraints. Change 'US state abbreviation (e.g., 'CA')' to an enum of valid state codes, or document the format as a regex pattern (2 uppercase letters).