Skip to main content
Glama

Search the geo.admin.ch STAC data catalogue

search_geodata_collections
Read-only

Search Swiss federal geodata collections by keyword to find downloadable datasets and their IDs, licences, providers and time extents; omit keywords to page through all collections.

Instructions

Keyword search over the downloadable federal geodata collections on data.geo.admin.ch (STAC): swisstopo elevation/imagery/maps, BAFU/BFE/ARE datasets and MeteoSwiss open data, e.g. 'ch.meteoschweiz.ogd-smn' (SwissMetNet automatic weather stations), 'ch.meteoschweiz.ogd-nime' (manual precipitation), 'ch.meteoschweiz.ogd-pollen'. Returns collection ids, titles, licence, providers and time extent. Next: get_geodata_collection_items. Examples: query='meteoschweiz', 'swissalti3d', 'Lärm'. Omit query to page through all collections.

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_geodata_collections"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax collections (default 20)
queryNoKeywords matched against id, title, description, keywords and providers (all must match)
offsetNoSkip this many matches (paging)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external-query behavior are covered. The description adds genuinely useful context beyond that: the fields returned (collection ids, titles, licence, providers, time extent) and that query-less calls enumerate everything. It says nothing about rate limits, auth, or result-size caveats, so the addition is helpful but thin.

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-loaded with the resource and scope, and every sentence carries information: domain, return fields, next tool, examples, paging fallback. The inline list of MeteoSwiss collection ids is slightly dense but serves as concrete grounding rather than filler.

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?

For a three-parameter, annotation-covered search tool with no output schema, the description supplies domain scope, successful-query examples, described return fields, paging behavior, and the natural follow-up tool. An agent has everything needed to decide to call it and to construct a working call.

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% and the schema already explains that query matches id, title, description, keywords and providers, so the baseline is 3. The description earns above-baseline credit by supplying real example query terms (including a non-ASCII one, 'Lärm') and by clarifying that an omitted query pages through all collections, which is a behavioral hint about the parameter the schema does not spell out.

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 verb (keyword search) and a precise resource (downloadable federal geodata collections on data.geo.admin.ch, STAC), then narrows the domain with named providers (swisstopo, BAFU, BFE, ARE, MeteoSwiss) and sample collection ids. This clearly separates it from generic siblings such as search_datasets or search_library_catalogue.

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

Usage Guidelines4/5

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

Gives an explicit workflow hand-off ('Next: get_geodata_collection_items') and covers the degenerate case ('Omit query to page through all collections'), plus concrete query strings like 'meteoschweiz' and 'Lärm' that show acceptable input style. It stops short of stating when a different sibling catalogue search would be the better choice, so it is not a full when/when-not/alternatives statement.

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

Deploy Server

Other Tools