Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Both tools have action-verb names (get_*) and non-empty descriptions (48-56 chars), meeting minimum thresholds. However, parameter descriptions are minimal, output schemas are not documented, and error handling guidance is absent. The 'days' parameter in get_forecast has a default but lacks min/max constraints. No tool annotations (readOnlyHint, etc.) despite READ_ONLY risk classification. Schemas are present but sparse, only 'city' and 'days' parameters documented, no return type specifications visible in source.

• Document output schemas for both tools. Example: get_current_weather returns {temperature: number, condition: string, humidity: number, wind_speed: number}. Include all fields the LLM needs to reason about weather.
• Add min/max constraints to 'days' parameter: minimum 1, maximum 5. Update description to 'Number of days to forecast (1-5, default 3)' and validate server-side.
• Expand tool descriptions to 100-150 chars. Example: 'Get current weather conditions (temperature, humidity, wind) for a city. Use this for immediate conditions; use get_forecast for multi-day planning.'
• Add readOnlyHint: true to both tool schemas to signal safety. Update tool registration in main.py to include annotations in the tool definition.
• Include error recovery hints in descriptions. Example: 'If city not found, try searching with region/country (e.g., "London, UK" or "New York, US").' This guides LLM retry logic.