atlas_asset_class_report
ChatGPTProfiles ONE asset class (office, retail/business, warehouse, residential, ...) in a single call: for-sale and for-rent aggregates, a building-class (A/B/C) breakdown, the top municipalities by asking value, month-over-month velocity, AND the total stock of that use — property count plus built area — which yields shareOfStockListed, the percent of the stock currently on the market. Use this instead of chaining atlas_get_stats + atlas_top_by + atlas_velocity by hand. COST: this runs ~7 metered queries and is billed as such (reported in meta.creditCost) — it saves round-trips, not credits. Outlier-flagged placeholder prices are excluded from every money figure, and the area sum drops impossible outliers (see inventory.excludedByAreaCap — quote it with the total). Read meta.notAvailable before reporting anything it lists as missing, and never estimate those.
atlas_comparable_sales
ChatGPTTHE tool for "what did comparable properties actually sell for". Returns RECORDED SALES (registry transactions — real closed prices, not asking prices) near a coordinate, each with its distance from the subject and price per m², plus the median sale price and median price per m² already computed. Optionally returns comparable active listings alongside them, clearly separated — those are ASKS and are not sale evidence. Use this for any valuation, offer-price, underwriting or "is this priced fairly" question. A near/bbox query on transactions is refused (that index has no coordinates), so this is the ONLY way to reach sales by location — never conclude comparable sales are unavailable in Atlas without calling it. PASS THE SUBJECT'S builtArea, lotArea, rooms and toilets whenever you know them: the matching is a similarity search, and comps chosen without them are merely nearby rather than comparable. Runs the comparables report and waits for it (usually seconds); if generation is still running when the wait budget ends you get status "processing" and a reportId to poll with atlas_get_report. Charges the report cost once, reported in meta.creditCost.
atlas_create_comparables_report
ChatGPTStarts a market-comparables report around a subject property: similar LISTINGS and — unless you turn it off — the RECORDED SALES near it, each with its distance from the subject. This is the Atlas source for "what did comparable properties actually sell for"; recorded sales are registry transactions, not asking prices. Async like AVM — poll atlas_get_report for the result, or call atlas_comparable_sales to do the create and the polling in one step. Charges credits per report (see meta.creditCost).
atlas_enrich_contacts
ChatGPTOwner/occupant contact data (names, phones, emails, addresses) for a US/Puerto Rico address or person, via skip-trace. BEST WAY TO CALL IT: pass parcelId (+ market) and nothing else — Atlas then builds the query from its own records (the parcel postal address, and in Puerto Rico the owner roll's name), which matches far more often than a listing address does. Resolve the parcelId with atlas_query_data on parcels, or from a listing's parcelId field. Without a parcelId, search by ADDRESS ALONE (numbered street line + city + zip, NO name); add firstName/lastName only to narrow an address search that returned several people. The vendor matches PERSONS only — never put a company, church or organization name in lastName. Queries that cannot match (a development name with no house number, an organization, a bare surname) are REFUSED with a 400 before any vendor call, so read the error hint and fix the query instead of retrying variations. Premium: charges the contacts_enriched credit price per call (echoed in meta.creditCost) whenever contacts are DELIVERED — a no-match costs 0 credits. Repeat lookups of the same subject are served from the RED Atlas store at the same price (data.servedFrom tells which; data.resolvedQuery shows what was actually searched). Only call when the user explicitly needs owner/contact data; for parcel-linked contacts already in Atlas prefer atlas_get_parcel_contacts.
atlas_get_parcel_contacts
ChatGPTReturns enriched contact information for a parcel. Premium feature: requires a plan with contact enrichment and charges extra credits per call (meta.creditCost). Only call when the user explicitly needs owner/contact data.
atlas_get_record
ChatGPTFetches one record by id for an entity type in a market. Costs credits for the fields returned; use fields to limit them. Includes the canonical atlasUrl app link for listings/parcels/properties.
atlas_get_report
ChatGPTFetches one report, including its result once status is "completed" and a shareable publicUrl. Free. Poll this after atlas_create_avm_report or atlas_create_comparables_report until status leaves "processing"; a report that ends "abstained" or "failed" was not charged and errorMessage/errorDetail say why.
atlas_get_stats
ChatGPTAggregated statistics for a (market, entity) pair — counts, price/area aggregates, percentiles, distributions and derived metrics (e.g. derived.pricePerBuiltAreaMedian). Optionally add an ad-hoc groupBy breakdown, custom percentiles, or an outlier-robust trimmed mean. On listings and transactions the response also carries excludingOutliers — the same price aggregates computed without the documents ingest flagged as isOutlier (scraped placeholder prices such as a $99,900,000 "call for price" listing). QUOTE excludingOutliers FOR ANY MONEY TOTAL OR AVERAGE; the top-level priceStats is the unfiltered figure and can be inflated by a handful of placeholders. Charges a fixed credit cost (reported in meta.creditCost). Supports the same filters as atlas_query_data.
atlas_list_entities
ChatGPTLists the entity types (properties, listings, parcels, …) available in a market and their endpoints. Free. Start here when unsure what data a market has.
atlas_list_reports
ChatGPTLists the account’s generated reports (all plans). Free.
atlas_lookup_location
ChatGPTTranslates human location names into the stable ids (regionId, cityId, neighborhoodId, …) that atlas_query_data filters expect, and returns boundary polygons. Free (0 credits). kind-specific parameters: cities accepts regionId; neighborhoods accepts cityId; sub-neighborhoods requires neighborhoodIds; zip-codes requires zipCode; buildings requires name and accepts cityId/neighborhoodId. Set includeGeometry to get GeoJSON boundary polygons for markets, regions, cities, neighborhoods, sub-neighborhoods and zip-codes — polygons are large, so keep size small and raise simplify (degrees; higher = coarser) if the result is truncated. sectors/sub-sectors/micro-sectors are a shared property-USE classification (e.g. "Office"), NOT geographic areas — name lookups with no polygon; sub-sectors accepts sectorId and micro-sectors accepts subsectorId to scope to a parent. They apply to properties, permits, tenants and parcels; a TRANSACTION sectorId is a deed type (sale, mortgage, ...) listed in the transactions field guide, not one of these.
atlas_market_profile
ChatGPTFull market profile for ONE location (a whole market, a region, a city, a neighborhood or a sub-neighborhood): sale and lease medians with monthly series, inventory, days on market, yield, demographics, quality-of-life scores, nearby POIs and local news — in a single call. Resolve the locationId with atlas_lookup_location first. EVERY metric is an envelope: { value, unit, yoy, vsParent, series, availability, caveats } plus optional sourcePeriod { kind, start, end, label? }, captureAsOf. Prefer sourcePeriod for the value; absent means unknown. Live stock uses captureAsOf, independent of snapshot series. Supply/absorption carry inventory captureAsOf and the lagged deed sourcePeriod window. Never date surveys with meta.generatedAt. Read availability before quoting a number — "unavailable" means we genuinely cannot compute it (listed with the reason in meta.notAvailable), and "partial" means the value is real but the caveats change how it should be read (e.g. deed_lag_truncated_12mo, mixed_census_vintages, current_value_only). Never present a metric without its caveats, and never fill an unavailable metric from another source.
atlas_market_report
ChatGPTProfiles a market in a single call: the aggregated stats block (counts, price/area aggregates, percentiles and derived metrics like median price per m²), a count-per-month trend for the last year, and — when groupBy is set — a ranked breakdown by that dimension. Use this instead of chaining atlas_get_stats + atlas_top_by when you want an overview. Billed as one aggregator call (meta.creditCost), the trend/breakdown add no extra cost.
atlas_pivot
ChatGPTCross-tabulates two fields (x by y) with per-cell counts and an optional metric — heatmap/matrix data (e.g. propertyType by city). EITHER AXIS MAY BE A DATE FIELD (createdAt, transactionDate, date): it is then bucketed as a calendar period via interval, which is how you get a per-group TIME SERIES — e.g. xField=propertyType + yField=transactionDate + interval=quarter returns quarterly counts per property type in ONE call instead of one query per period. Charges a fixed credit cost (meta.creditCost).
atlas_query_data
ChatGPTLists records of an entity type in a market with pagination, filters, sorting and field projection. Costs credits per record returned — keep limit small and use fields to request only what you need. Each record includes a server-built atlasUrl (canonical app link) for listings/parcels/properties — link to that, never to a record's source url. Response envelope: { data, meta (creditCost), rateLimit (limit/remaining/reset) }.
atlas_read_docs
ChatGPTReads the official RED Atlas API docs. Without a topic it returns the section index; with a topic (e.g. "filtering", "credits", "rate limits", "avm") it returns the matching sections. Free. Prefer this over guessing parameters.
atlas_search
ChatGPTFree-text search across entity types in a market (addresses, names, places). Charges credits per call. Returns grouped hits per entity bucket; follow up with atlas_get_record for full details. On a lower plan, find records with atlas_query_data + an address.like filter instead.
atlas_top_by
ChatGPTTerms aggregation: the top values of groupBy (e.g. propertyType, status, cityId) with their record counts and an optional sub-metric. One call replaces paging + manual counting. Charges a fixed credit cost (meta.creditCost).
atlas_velocity
ChatGPTHow fast a market is moving: the count of new records in the current period vs the previous equal-length period, with the absolute and percent change. E.g. new listings or permits this month vs last month. Charges a fixed credit cost (meta.creditCost). Entities without a usable date field return an error — pass dateField to override the default.
atlas_create_avm_report
Claudeatlas_create_comparables_report
Claudeatlas_get_parcel_contacts
Claudeatlas_get_record
Claudeatlas_get_report
Claudeatlas_get_stats
Claudeatlas_list_entities
Claudeatlas_list_reports
Claudeatlas_lookup_location
Claudeatlas_market_report
Claudeatlas_pivot
Claudeatlas_query_data
Claudeatlas_read_docs
Claudeatlas_search
Claudeatlas_top_by
Claudeatlas_velocity
Claude
