FindEstate Real Estate

Show FindEstate property map

search_findestate_map

Read-onlyIdempotent

Search and show an interactive property map inside ChatGPT. For any request to show results on a map, call this tool directly with all requested filters, locale and limit. It already opens the map UI; do not call render_findestate_properties afterward, because a reference-only render replaces the map and cannot carry its search context. Use this for requests such as new apartments in Vilnius on a map. Supports country, city, property type, sale/rent, original-currency price and area, plus phase=new and developer for individual properties linked to a currently approved new-development project. Every result rechecks BOTH GEO and MCP permission, current source and field freshness. Coordinates describe the published project location, not an exact apartment; preserve precision and evidence. Missing coordinates stay in the list. mappedCount and missingCoordinatesCount describe this returned batch. totalCount is the exact authorized match count at asOf; it is never all city or national inventory. Filters, sorting and optional confirmed-project grouping apply before pagination across this authorized scope; preserve returned order and follow nextCursor with identical filters. Rooms and bedrooms are distinct current published facts; missing required facts cannot pass. Preferences are soft. Monetary sorting requires an explicit sale/rent transaction and original currency; rental billing periods are not normalized. No invented geocoding, center/proximity or amenity criteria, investment returns, reservations or payments. Individual cards retain explicit guest viewing/question forms.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_findestate_map"
  }
}

Input Schema

Name	Required	Description	Default
`city`	No
`kind`	No		properties
`floor`	No
`limit`	No
`phase`	No
`query`	No
`rooms`	No	Explicit total room count, distinct from bedrooms. Unknown facts cannot satisfy this requirement.
`cursor`	No
`locale`	No		en
`sortBy`	No	Global ordering within current authorized matches before pagination. Price sorts require currency and sale/rent. observedAt is observation time, not listing creation. match counts matched wishes for this query only.
`country`	No
`maxArea`	No
`minArea`	No
`bedrooms`	No	Explicit bedroom count only. Never derive this from total rooms or assume rooms minus one.
`currency`	No
`maxFloor`	No
`maxPrice`	No
`maxRooms`	No
`minFloor`	No
`minPrice`	No
`minRooms`	No
`developer`	No
`projectId`	No	Exact confirmed parent-project catalog ID, never a guessed association.
`sortOrder`	No
`maxBedrooms`	No
`minBedrooms`	No
`preferences`	No	Optional wishes only. Flat filters remain mandatory and are never relaxed; unknown wishes are explained separately.
`transaction`	No
`maxYearBuilt`	No
`minYearBuilt`	No
`propertyType`	No
`excludeFloors`	No
`maxPerProject`	No
`groupByProject`	No

Output Schema

Name	Required	Description	Default
`asOf`	No
`items`	Yes
`status`	Yes
`filters`	Yes
`hasMore`	No
`version`	Yes
`coverage`	Yes
`browseUrl`	Yes
`nextCursor`	Yes
`totalCount`	No
`resultSetCount`	No
`totalCountRelation`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/destructive annotations it discloses real behavior: every result rechecks GEO and MCP permission plus source/field freshness, filter/sort/grouping apply before pagination across the authorized scope, and cursors must be followed with identical filters and preserved order. It also explains result semantics (coordinates are project-level not unit-level, missing coordinates still list, mappedCount/missingCoordinatesCount describe the batch, totalCount is an authorized-match count and never full inventory), which the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The operative instruction (call directly, don't chain the render tool) is front-loaded in the first two sentences, and the dense parameter/behavior notes follow. A few sentences are cryptic or feel bolted on, notably "Individual cards retain explicit guest viewing/question forms" and the unexplained GEO/MCP recheck phrasing, which cost it the top mark on a long description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 34-param, nested-schema tool with an output schema, this covers the decisions an agent must get right: when to call, when not to chain, how pagination and ordering behave, and what the returned counts mean. The remaining gap is the untouchable filter families (floors, year built, free-text query, kind), which an agent must infer from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 15% schema description coverage across 34 params, the description carries real weight: it explains rooms vs bedrooms as distinct published facts, original-currency price/area, phase=new and developer/projectId scope, that preferences are soft while flat filters are mandatory, and that monetary sorting needs an explicit transaction and currency with rental periods un-normalized. It still leaves floor/min-max floor, excludeFloors, yearBuilt, query, kind and sortOrder undiscussed, so coverage is strong but not complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Search and show an interactive property map inside ChatGPT" states a specific verb pair (search + render map) and resource, and immediately distinguishes itself from render_findestate_properties, which it explicitly says not to call afterward. An agent can tell what this does and how it differs from the render and search siblings without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger ("For any request to show results on a map"), an explicit anti-pattern ("do not call render_findestate_properties afterward, because a reference-only render replaces the map"), and a worked example ("new apartments in Vilnius on a map"). It also closes off out-of-scope intents (no geocoding, center/proximity, amenities, investment returns, reservations, payments), which is exactly the negative guidance an agent needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FindEstate Real Estate tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?