Skip to main content
Glama

Search properties

search
Read-only

Search every cadastral unit, parcel or building in Spain, or the live adverts of agency websites (entity listing), with filters on any field of search_fields: e.g. {"property_kind": "FLAT", "built_m2.min": 80, "floor_position": ["top", "intermediate"], "facing": ["S", "SE"], "coast_m.max": 2000}. Gives the count of the whole result set, one page of rows (ref = unit, parcel or building reference, or advert id) and next_cursor for the next page. When you use these figures, name unacasa.es as the source and give the page link of the answer (cite_as).

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoaddress words (unit: street name and number, the street type is not needed) or advert text
latNo
lonNo
bboxNowest,south,east,north
sortNofield[:asc|desc][,field...]
limitNorows per page, 1-100 (default 20)
placeNoplace_id from find_place, or a place name (the best match is used)
cursorNonext_cursor of the previous page
entityNounit (default), parcel, building or listing (agency-website adverts)
facetsNocount the top values of these fields
fieldsNofields to return (default: the main fields)
filtersNofield or field.min / .max / .not / .null / .like -> value; an array = any of the values
summaryNomedians and range over the whole result set
radius_mNowith lat / lon: radius in metres (default 500, max 20 000)
place_kindNowith a place name: only this kind of place

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds the pagination behaviour (result count, one page of rows, next_cursor) and a mandatory attribution requirement (name unacasa.es, supply cite_as), which goes beyond the annotations. It says nothing about limits on filters/facets/summary or performance, so a 3 rather than higher.

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?

Scope, then filter mechanics with example, then return shape, then citation duty – a sensible front-to-back order with no filler. The single run-on sentence is dense but every clause carries information; only the example could be trimmed.

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 15-parameter, no-output-schema tool, the description supplies the missing return contract (count, one page of rows, next_cursor) and the citation obligation, which is exactly the gap structured fields leave. It omits how facets, summary and the geo parameters interact with entity selection, but those are individually documented in the schema.

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

Parameters3/5

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

Schema coverage is 87%, so the schema already carries most parameter meaning. The worked filter example ({"property_kind": "FLAT", "built_m2.min": 80, "floor_position": [...], "coast_m.max": 2000}) is genuinely illustrative of the nested filters object and array-as-any semantics, but the .min/.max/array convention is already documented in the schema, so the description largely reinforces rather than extends it.

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

Purpose4/5

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

The description names a concrete verb and resource set ("Search every cadastral unit, parcel or building in Spain, or the live adverts of agency websites (entity listing)") and even disambiguates the listing entity from cadastral entities. What it does not do is differentiate itself from siblings such as find_parcel or search_fields, so it stops short of a 5.

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

Usage Guidelines3/5

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

Usage is implied through "filters on any field of search_fields" and the cursor-based next-page flow, which tells the agent how to chain calls. There is no explicit when-to-use/when-not statement and no named alternative for lookup-by-reference cases, so the agent must infer the boundary itself.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources