Skip to main content
Glama

Find Swiss data across every catalogue

find_data
Read-only

Search connected Swiss public data catalogues in one query and get ranked hits with the exact tool and arguments to retrieve each dataset.

Instructions

START HERE for any Swiss data question not obviously covered by a specific tool. Searches all connected catalogues at once: opendata.swiss (12'000+ datasets), the federal geodata layers (geo.admin.ch, ~900 layers + STAC), BFS STAT-TAB statistical tables, LINDAS statistical cubes, cantonal/SBB Opendatasoft portals, SNB data, and returns ranked hits. Every hit includes next: the exact tool and arguments that fetch the actual data (invoke it directly, or via call_tool if that tool isn't loaded). Example queries: 'rent prices Zürich', 'Strassenlärm', 'Übernachtungen Hotels', 'parking Basel', 'Radon'. German terms often match best.

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": {
      "query": "<query>"
    },
    "name": "find_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNode
limitNo
queryYesWhat you are looking for, e.g. 'bicycle counts', 'Mietpreise', 'noise map'
cataloguesNoOptional subset of catalogue names to search (see the `catalogues_searched` field of a previous result)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behaviour not present there — that results are ranked across federated catalogues, and that every hit carries a `next` field naming the exact tool and arguments to fetch the data. That disclosure of return shape and chaining mechanics is critical given there is no output schema.

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 routing instruction is front-loaded and the catalogue inventory plus example queries are compact and high-value. The long enumeration of sources is slightly dense but each item tells the agent something about coverage that the schema cannot.

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 federated search with no output schema, the description supplies the two things an agent most needs: what corpus is being searched and what the result objects contain (`next` plus a `catalogues_searched` field referenced for reuse). No significant call-time question is left unanswered.

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 50%, so the schema already documents `query` and `catalogues`; the description adds meaning mainly for language choice ('German terms often match best') and by listing available catalogues. It says nothing about how to use `limit` or how deep the ranked result set goes, so a baseline 3 is appropriate.

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 description names a specific verb and resource (searches all connected Swiss catalogues at once, returns ranked hits) and explicitly enumerates the sources covered. It also positions itself against siblings with 'not obviously covered by a specific tool,' so an agent can decide between find_data and the specialised data tools without opening schemas.

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 entry-point condition ('START HERE for any Swiss data question not obviously covered by a specific tool') and supplies an exclusion rule pointing at specialised tools. It goes further by explaining the follow-up path ('invoke it directly, or via call_tool if that tool isn't loaded') and gives concrete example queries plus a language tip, leaving little to inference.

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