Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the fare watch agent end-to-end: collect current prices from Amadeus, compare against thresholds, generate alerts, return full AgentResult.
- analyze_prices — Given raw flight offer data, run pure deterministic threshold analysis and return scored findings. No LLM.
- check_alerts — Quick check: run the fare watch pipeline and return only active price alerts. Faster than run_full.
- get_route_history — Get price history for a specific route (mock fixture in test mode; Google Sheets in production).
- discover_intent — Understand your goal and co-design the exact input via clarifying questions before running.
- plan_inputs — Plan/brainstorm the inputs for a tool: returns questions, schema and a ready-to-edit example.
- list_capabilities — List the agent's static capabilities.
