Skip to main content
Glama

Get geodata

get_geodata
Read-only

Geodata from a state's service around the served model: kind parcels, buildings or terrain. Asks the service once and keeps the answer as a reference of the room (reference_id, shown in the viewer); the model file stays untouched. The area: the model's box through its georeference plus area.margin_m (default 50); edge_m only for a model without elements, a square around the map origin. An answer in another EPSG than the model's, or in longitude and latitude, is converted to it; source names service, fetched_at and the conversion with its rule and delta_m. Without a path the call is refused with the reason. parcels and buildings: a row per feature with the properties the service gave and its outline in project m (parts of rings [x, y]); first the feature the model box lies in, then by distance_m from that box to the outline: a box holds the footprint, so distance_m is at most the true one. terrain: cells, cell size in metres of the service EPSG, NoData cells (masked, never filled) and the height range in project m. Every answer names service, fetched_at, licence and credit; a credit goes with whatever is built from it. coverage counts the rows listed against the features kept. More: read_reference with reference_id reads the kept answer, never asking again. Each call asks the service and counts against a limit per caller (RATE_LIMITED, detail.retry_after_s). Double-check an outline against points you know before you build on it. Read-only for the model.

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": {
      "kind": "<kind>"
    },
    "name": "get_geodata"
  }
}

Input Schema

NameRequiredDescriptionDefault
areaNoThe box asked; default: the model box plus 50 m
kindYesWhat to ask the service for
sourceNoA service id; default: the one covering the largest share of the model's place for kind. The answer lists those at this place (sources, covered_share)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations it discloses that the service is queried on every call, the result is persisted as a reference visible in the viewer while the model file is untouched, EPSG/longitude-latitude conversion with rule and delta_m, NoData cells masked and never filled, and licence/credit obligations. These details materially extend readOnlyHint/openWorldHint/idempotentHint rather than restate them, and are consistent with idempotentHint=false and openWorldHint=true.

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?

The content is dense and front-loaded, but delivered as long semicolon-chained fragments that are hard to parse, mixing usage rules, geometry semantics, and return-shape detail without headings. Little is redundant, yet the telegraphic style costs readability for a tool this important.

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 no output schema, the description deliberately carries the return shape — per-feature rows with properties and ring outlines in project metres, ordering by distance_m, terrain cells and height range, coverage counts, and service/fetched_at/licence metadata. For a 3-parameter, nested-object tool with open-world network behavior, this covers what an agent needs to call it and interpret the result.

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 description coverage is 100%, so the schema already documents kind, area.margin_m, area.edge_m, and the source default rule; the description largely repeats those defaults. It adds some framing (the model box through its georeference, edge_m only for a model without elements), but no syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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?

The opening sentence gives a specific verb and resource — pulling geodata (parcels, buildings, terrain) from a state's service around the served model — and the closing sentences distinguish it from read_reference, which reads a kept answer instead of asking the service again. An agent can identify the operation and its scope without opening the 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 states the selection rule for the alternative (read_reference with reference_id reads the kept answer, never asking again), gives preconditions (without a path the call is refused with the reason), a caution before building on results, and the cost model (counts against a per-caller limit, RATE_LIMITED with detail.retry_after_s). Explicit when-to-use, when-not, and consequence.

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