Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run end-to-end: read listings (read-only), score completeness, detect optimizations, synthesize a narrative (LLM with template fallback), return the full AgentResult JSON.
- fetch_listings — Read-only fetch of listings (mock fixtures / provided data). No writes. Returns the raw listing batch.
- score_completeness — Deterministic completeness scoring for given listings: per-listing 0-100 score and missing required fields. No LLM.
- detect_optimizations — Deterministic optimization detection for given listings: issues + prioritized recommendations + price deviation. No LLM.
- list_capabilities — List static capabilities: tools, required fields, default thresholds, and credential slots.
- plan_inputs — Plan/brainstorm the inputs for a tool: returns the questions, schema and a ready-to-edit example.
