AuctionScout

Add an auction to the user's wishlist. Idempotent. Auto-creates a reminder (1 day before, falling back to 1 hour).

add_to_wishlist

Comparable sales, area statistics, risk factors, and LTR/BRRRR/Flip deal metrics for one auction. Numbers only — no AI narrative.

analyze_auction

Create a reminder for an auction. minutes_before must be 15, 60, or 1440.

create_reminder

Save a named search with filters. `filters` is a predictions-filter object — see the schema for the exact fields. Range filters such as market_price_range are 2-element [min, max] arrays (e.g. [0, 500000]), not {min, max} objects. Alerts default to off; use the portal to configure alert frequency.

create_saved_search

Full detail for one auction, including parcel id, county auditor/clerk URLs, and a (DB-only) estimates bundle. Estimate fields may be null.

get_auction

Upcoming auctions with model-predicted sale prices and confidence scores. Auctions without a prediction row are included with prediction=null. Filter by county, min_confidence, or max_days_ahead. Up to 50 rows. ROI is calculated as (market_estimate - predicted_price) / predicted_price * 100.

get_predictions

Cached neighborhood data for an auction (looked up by auction_id). Sections: schools (district name, PI rating), amenities (nearby grocery/dining/parks/etc. and walkability score), demographics (census tract income/population/home values). Returns null for any section not yet in cache — no live API calls are made.

get_neighborhood

The user's auction reminders. Call with NO arguments to list every reminder they have; pass auction_id to list only that auction's reminders. Each row includes the auction address and date.

list_reminders

Return the authenticated user's saved searches.

list_saved_searches

Return the user's wishlisted auctions. filter: 'upcoming' (default) | 'past' | 'all'.

list_wishlist