Skip to main content
Glama

Houski Property Data

aggregate_endpoint

Get statistical aggregations for market analysis. Billed per aggregate value returned. Aggregations: count, sum, mean, median, mode, min, max, quantile-10, quantile-25, quantile-40, quantile-60, quantile-75, quantile-80, quantile-85, quantile-90, quantile-95, quantile-99. Text and boolean fields only support count and mode, and only fields field_detail marks aggregatable are accepted. count counts the properties that hold a value for the field, so a count per country measures how well a field is covered there. Ask for several statistics in one call with the aggregations array instead of one call each.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "api_key": "<api_key>"
    },
    "name": "aggregate_endpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity name. Requires country_abbreviation and province_abbreviation, and the request is refused with a 400 error if either is missing.
fieldNoField to aggregate for a single statistic. Use field_list to discover available fields. Leave this out when using aggregations.
api_keyYesAPI key for authentication
excludeNoSource classes to leave out of the aggregation, comma separated: "inferred" leaves out every value Houski worked out, and "inferred,observed" keeps only values from a linked public record. Applies to a field with a source column, and the answer's values_used counts the values each statistic used. In the aggregations form every entry inherits it unless it sets its own.
filtersNoFilters array. Format: "field_operator=value", with the value as plain text and not URL encoded. Use search_api_documentation for reference.
polygonNoPolygon coordinates "lat_lng,lat_lng,lat_lng", latitude and longitude joined by an underscore. Maximum 100 points, simplify a shape that has more.
communityNoCommunity/neighborhood name. Requires country_abbreviation, province_abbreviation and city.
aggregationNoAggregation type for the single-statistic form: count, sum, mean, median, mode, min, max, quantile-10, quantile-25, quantile-40, quantile-60, quantile-75, quantile-80, quantile-85, quantile-90, quantile-95 or quantile-99. Those quantiles are the only ones that exist.
bbox_ne_latNoBounding box northeast latitude. All four bbox values are required together.
bbox_ne_lngNoBounding box northeast longitude. All four bbox values are required together.
bbox_sw_latNoBounding box southwest latitude. All four bbox values are required together.
bbox_sw_lngNoBounding box southwest longitude. All four bbox values are required together.
price_quoteNoReturn the cost of this request without billing it or returning data
aggregationsNoSeveral statistics in one request, instead of one call each. Each entry gets its own field and aggregation, and inherits this call's location and filters unless it sets its own. Do not also set field.
country_abbreviationNoCountry abbreviation as location_endpoint returns it (for example "CA"). Any letter case is accepted.
province_abbreviationNoProvince, state or region abbreviation as location_endpoint returns it (for example "AB"). Requires country_abbreviation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses the billing model ("Billed per aggregate value returned"), the field-type restriction (text and boolean fields only support count and mode), the aggregatability gate enforced by field_detail, and a non-obvious semantic ("count counts the properties that hold a value," so count measures coverage). What is missing is any statement of response shape, error behavior, or auth/cost expectations beyond the per-value billing note.

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

Conciseness3/5

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

Purpose and billing are correctly front-loaded, but the 16-item quantile enumeration duplicates the schema verbatim and consumes a large share of the text for zero added information. The remaining sentences each carry real rules, so the waste is concentrated rather than diffuse.

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

Completeness3/5

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

For a 16-parameter tool with no annotations and no output schema, the description covers the aggregation semantics well but says nothing about what the response contains (structure, values_used, how statistics are keyed per entry) — the one thing the absent output schema would otherwise have supplied. Location parameters (bbox, polygon, city, community) are left entirely to the schema.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: the coverage-count interpretation of `count` and the constraint that only field_detail-flagged aggregatable fields are accepted — both affect how an agent picks `field`. The exhaustive quantile list, however, simply restates what the schema already enumerates.

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 opens with a specific verb and resource: "Get statistical aggregations for market analysis," then enumerates the supported aggregation types and their field-type restrictions. It is unmistakably an aggregation tool rather than a search or property-lookup tool, though it never names which sibling (search_endpoint, properties_endpoint) to reach for when the agent wants raw records instead of statistics.

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?

It gives one concrete usage rule — batch multiple statistics via the aggregations array rather than making repeated calls — and points to field_list/field_detail for discovery. But it gives no guidance on when this tool is the right choice versus record-returning siblings, and no exclusions. Usage is implied by the statistical framing rather than stated.

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