Two tools with minimal documentation. create_ticket has a basic schema (title, priority with default) but lacks parameter descriptions and output schema documentation. get_weather has only a location parameter with minimal context. Both descriptions are in Spanish and under 100 chars, providing insufficient context for LLM tool selection. No error handling guidance, no output schemas documented, no parameter constraints (enums, ranges). Tool definitions are partially inferred from code rather than explicitly registered with full metadata.

• Add parameter descriptions to both tools. For create_ticket, document priority as 'Ticket priority level (low, normal, high, urgent)' with an enum constraint. For get_weather, clarify location format: 'City and country, e.g. Madrid, Spain or Madrid, ES'.
• Document output schemas formally. For create_ticket, specify: {id: string, url: string, title: string, priority: string}. For get_weather, return structured JSON {temperature: number, unit: string, condition: string, location: string} instead of free-text.
• Add error handling and recovery guidance. E.g., 'If priority is invalid, valid options are: low, normal, high, urgent. If location is not found, try a larger region (e.g., Spain instead of Madrid).'
• Consolidate tool definitions. Move get_weather from app/main.py into mcp_server/server.py as a FastMCP-decorated function so all tools are registered consistently and discoverable.
• Expand tool descriptions to 50 - 150 characters. Current descriptions (e.g., 'Obtiene la temperatura actual de una ciudad') lack context for when/why to use the tool. Add: 'Use this to check current weather conditions before planning outdoor activities or advising on clothing.'