GeoSpark

Overture Maps features

overture_features

Read-onlyIdempotent

Open global map data from Overture Maps, no API key: points of interest (with categories), building footprints (height, floors, geodesic footprint area), road and path segments (geodesic length), or divisions, the administrative areas containing the point (country, region, city, neighbourhood). Results are nearest first, with distances in metres. Can take 5-20 s on a cold cache.

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": {
      "theme": "<theme>",
      "latitude": "<latitude>",
      "longitude": "<longitude>"
    },
    "name": "overture_features"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum number of features to return, nearest first
`theme`	Yes	Which data: places (points of interest), buildings, transportation (road and path segments) or divisions (areas containing the point)
`category`	No	Places only, e.g. 'cafe'
`latitude`	Yes	Latitude in degrees (WGS84)
`radius_m`	No	Search radius in metres
`longitude`	Yes	Longitude in degrees (WGS84)

Output Schema

Name	Required	Default
`bbox`	No
`type`	No	FeatureCollection
`features`	Yes
`geospark`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

addedInput schema / properties / limit / description

Added value: +"Maximum number of features to return, nearest first"

addedInput schema / properties / theme / description

Added value: +"Which data: places (points of interest), buildings, transportation (road and path segments) or divisions (areas containing the point)"

First observedOct 23, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, open-world behavior, so the safety profile is covered. The description adds genuinely new context: results come nearest-first with distances in metres, and cold-cache calls may take 5–20 s. It does not mention rate limits or max result caps, but the latency disclosure is the practically important one.

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?

Front-loads the data source and the no-key selling point, then enumerates themes in one flowing sentence and closes with ordering and latency. It is dense but every clause carries information; minor parenthesis-heavy formatting is the only cost.

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

Completeness5/5

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

With an output schema present, the description needn't describe return shapes, and it doesn't. It covers source, per-theme content, ordering, units, and performance characteristics — everything an agent needs to decide whether and how to call it.

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 100%, so the baseline is 3. The description clarifies what each theme yields (e.g. that divisions are the areas containing the point, and that category applies to places), but adds nothing about radius_m or limit behavior beyond the schema's own prose.

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?

States a specific resource (Overture Maps open data) and enumerates exactly what each theme returns: POIs with categories, building footprints with height/floors/area, road segments with length, and administrative divisions containing the point. An agent can tell precisely what this retrieves and how it differs from geocode or reverse_geocode siblings.

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?

Implied usage is clear from the theme enumeration and the 'no API key' note, but there is no explicit guidance on when to choose this over geocode, reverse_geocode, or location_report. The agent must infer that this is for feature lookups around a coordinate rather than address resolution.

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

All GeoSpark 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.