Two tools with basic verb-noun naming (get_alerts, get_forecast). Both have short descriptions (34-40 chars, below the 50-200 char LLM-optimized baseline). Input schemas present with types and descriptions, but output is unstructured plain text strings rather than structured objects. No error handling guidance, no pagination support, no output schema documentation. Lacks composition patterns for chaining. Naming is acceptable but descriptions are too terse to guide LLM tool selection effectively.

• Expand tool descriptions to 80-150 chars. Example: 'get_alerts: Retrieve active weather alerts for a US state. Returns event type, severity, affected area, and instructions. Use when user asks about weather warnings or hazards.'
• Return structured JSON objects instead of formatted strings. get_alerts should return {alerts: [{event, area, severity, description, instructions}], count, state}. get_forecast should return {periods: [{name, temperature, temperatureUnit, windSpeed, windDirection, forecast}], location, generatedTime}.
• Document output schemas in tool descriptions or as JSON Schema. Example: 'Returns object with alerts array (each with event, area, severity, description, instructions fields) and total count.'
• Add error handling with recovery hints. Replace 'Unable to fetch alerts' with 'Failed to fetch alerts for state {state}. Verify state code is valid (e.g., CA, NY). If problem persists, try again in 30 seconds.'
• Add limit and offset parameters to get_forecast to support pagination. Example: limit (1-10, default 5) and offset (default 0). Return total_periods in response so LLM knows if more data exists.