Skip to main content
Glama

kataster_mapa

Draw selected Slovak cadastral parcels on a map with labels and background layers, then export PNG, interactive HTML, GeoJSON, or KML files and get their paths.

Instructions

Draw parcels on a map and save files. Returns the file paths.

PNG is rendered on the server (background from official WMS, outlines, labels, scale bar, attribution). HTML is an interactive Leaflet map with the same background embedded and, when the parcels lie apart, a sharp crop (vyrezy) per cluster of near parcels above it, so zooming in stays readable; each crop costs one request per background source (podklad_dotazy). GeoJSON/KML contain only geometry and public attributes (no owners).

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": {
      "parcely": "<parcely>"
    },
    "name": "kataster_mapa"
  }
}

Input Schema

NameRequiredDescriptionDefault
nazovNoBase file name; default derived from the parcels.
formatNoOutput files: png (rendered map), html (interactive Leaflet map), geojson, kml.
out_dirNoDirectory for the files; default <data dir>/mapy.
parcelyYesParcels to draw (max 50).
podkladNoBackground: orto (ZBGIS orthophoto), kn (cadastral map), orto+kn, osm (OpenStreetMap).orto
popiskyNoLabel parcels with register and number.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does reasonably well: it discloses that rendering happens server-side, what each output contains (PNG layers including scale bar and attribution; HTML interactive Leaflet), and that GeoJSON/KML carry only geometry and public attributes with no owners. It also warns that HTML crops trigger one background request per source, which is genuine cost/side-effect disclosure. Gaps remain: it never states that files are written to disk (a mutation side effect on out_dir), nor what happens on partial failures or oversized parcel lists.

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 core action and return value are front-loaded in one short sentence, and the remaining prose is dense with information rather than filler. Some phrasing is heavy ("a sharp crop (vyrezy) per cluster of near parcels above it") and mixes Czech jargon into the flow, slightly hurting readability. No sentence is purely redundant.

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 6-parameter, single-purpose export tool with full schema coverage and no output schema, the description covers the essentials, including what is returned (file paths) and what each format yields. It is thin on filesystem side effects and error/limit behavior, which matters for a tool that writes files. Overall adequate to call correctly, but not fully complete.

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 already 100%, so the baseline is 3, but the description adds real meaning beyond it: it explains what png versus html versus geojson/kml actually produce, and that the owner fields are stripped from the vector outputs. That is semantic value the enum alone does not convey. It says nothing extra about nazov, out_dir, or popisky (labels).

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?

States a concrete verb and resource: "Draw parcels on a map and save files. Returns the file paths." That clearly separates it from the sibling data-lookup tools (kataster_parcela, kataster_lv, etc.), which retrieve records rather than render/export. It stops short of naming a sibling or stating the boundary explicitly, so it is clear but not fully differentiated.

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 only implied: an agent can infer this is the tool for producing a visual map or geometry export. There is no explicit "use this when…" statement, no exclusion (e.g. use kataster_parcela for raw data), and the 50-parcel cap is left entirely to the schema. The note that each crop costs one request per background source is a useful cost hint but not selection guidance.

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