Skip to main content
Glama

Search Swiss open-data catalogues

search_datasets
Read-only

Search national and Zürich open-data catalogues by keyword, publisher, format, or date to locate datasets, then retrieve their metadata or queryable rows.

Instructions

Full-text search over the national open-data catalogue opendata.swiss (default) or the City of Zürich portal (portal='stadt-zuerich'): statistics (population, prices, energy…), geodata, transport, health and more. Each hit lists its resource formats and whether it is queryable (has CSV/JSON/GeoJSON). Filter by publisher (slug from list_data_publishers), by format (e.g. 'CSV'), sort by 'modified' for the newest. Then call query_dataset {id} for the actual rows, or get_dataset {id} for metadata. Examples: {query: 'Mietpreisindex'}, {query: 'Bevölkerung Gemeinde', format: 'CSV'}, {publisher: 'bundesamt-fur-statistik-bfs', sort: 'modified'}, {query: 'Velo', portal: 'stadt-zuerich'}.

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_datasets"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage for titles/descriptions: de, fr, it or en (default en; falls back to de)
sortNorelevance (default), modified (newest updates first), created, name
limitNo
queryNoSearch terms, e.g. 'rent index', 'STATPOP', 'Luftqualität'. German terms match best. Optional if publisher/format is given
formatNoOnly datasets with a resource of this format, e.g. 'CSV', 'JSON', 'GeoJSON', 'XLSX'
offsetNoSkip this many hits (paging)
portalNoCatalogue: 'opendata.swiss' (default, national), 'stadt-zuerich' (City of Zürich, data.stadt-zuerich.ch) or 'envidat' (WSL/ETH environmental research data: snow, glaciers, forests, biodiversity, climate)
publisherNoOptional publisher (organization) slug, e.g. 'bundesamt-fur-statistik-bfs'; see list_data_publishers

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description rightly focuses on what the results contain: each hit lists resource formats and a queryable flag for CSV/JSON/GeoJSON. That is genuinely useful behavioral context without an output schema, though it omits paging/limit behavior and any rate-limit or error characteristics.

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 primary resource and default portal, then filters, then next steps, then examples — a sensible priority order. It is dense and the trailing example list makes it longer than strictly necessary, but each sentence earns its place.

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 read-only search with no output schema, the definition covers what is searched, what a hit contains, how to filter/sort, and what to call next. Remaining gaps (paging guidance beyond the offset param, error or empty-result behavior) are minor for this tool class.

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 88%, so the schema already documents the enums, defaults and language fallback; the description's 'German terms match best' and 'modified (newest)' largely restate schema text. Its real marginal value is the worked examples showing how query, format, publisher, sort and portal combine — additive but not detailed per-parameter semantics.

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 and resource (full-text search over the national open-data catalogue, with a named alternate portal) and enumerates the content domains covered (statistics, geodata, transport, health). An agent can distinguish it from sibling searches like search_portal_datasets or search_bfs_tables from the description alone.

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?

Explicitly routes the agent to next steps: query_dataset {id} for rows, get_dataset {id} for metadata, and list_data_publishers for publisher slugs, plus 'sort by modified for the newest'. Concrete example invocations show each combination (query-only, query+format, publisher+sort, query+portal), 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