Skip to main content
Glama

Search LINDAS statistical data cubes

search_data_cubes
Read-only

Searches Swiss federal statistical data cubes by keyword across names, descriptions, publishers, and IRIs, returning cube metadata and visualize.admin.ch links for further exploration.

Instructions

Keyword search over the federal statistical data cubes on LINDAS (the data behind visualize.admin.ch): electricity prices (ElCom), energy statistics (BFE), environment/air/water (BAFU), agriculture (FOAG), traffic counts (ASTRA), population and economy (BFS) and more. Every word must appear (case-insensitive) in the cube's name, description, publisher or IRI, in any language (German terms often match best, e.g. 'Strompreis', 'Luft', 'Verkehr'). Returns cube IRI, name, trimmed description, publisher, last-modified date and a visualize.admin.ch link. Deprecated cube versions are excluded; published cubes shown on visualize.admin.ch rank first. Next step: describe_data_cube {cube: }. Examples: {query: 'electricity price'}, {query: 'Treibhausgas', lang: 'de'}, {query: 'bfe energie', limit: 10}.

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_data_cubes"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoPreferred language for names/descriptions (falls back to de/fr/it/en)en
limitNo
queryNoKeywords (all must match). Empty lists the most recently modified cubes.
offsetNo
published_onlyNoExclude cubes whose status is Draft

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 and openWorldHint, but the description adds real behavior: case-insensitive all-terms matching across name/description/publisher/IRI in any language, deprecated versions excluded, and published cubes ranking first. It also enumerates the return fields (IRI, name, trimmed description, publisher, last-modified, visualize link), which matters because there is no output schema. Pagination/total-count behavior and any expected latency are left unstated.

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?

A single dense paragraph that front-loads scope, then matching rules, then return fields, then the next step, ending with compact examples. Nearly every clause carries information, though the publisher acronym list (ElCom, BFE, BAFU, FOAG, ASTRA, BFS) is the least load-bearing part and could be trimmed.

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 5-parameter read-only search with no output schema, the definition covers what is searched, how matching works, ranking, exclusions, and what comes back — enough to call it correctly. The gaps are minor and consistent with the low-complexity tool: paging semantics for `offset`/`limit` and result-set size are not described.

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?

With 60% schema coverage, the description earns credit by explaining that every term in `query` must match and that matching spans multiple multilingual fields, plus examples showing `lang` and `limit` in use. `offset` and the interaction between `published_only` and the stated deprecated-exclusion rule remain unaddressed, so compensation is partial rather than full.

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?

Opens with a specific verb+resource ('Keyword search over the federal statistical data cubes on LINDAS') and immediately grounds it with the domain ('the data behind visualize.admin.ch') plus publisher examples (ElCom, BFE, BAFU, FOAG, ASTRA, BFS). It also names the sibling to use next (describe_data_cube) and the cube IRI it hands off, so an agent can tell this apart from query_lindas or search_datasets.

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 concrete invocation guidance: all words must match, German terms often match best ('Strompreis', 'Luft', 'Verkehr'), and three worked examples including lang and limit. It also states an explicit next step ('describe_data_cube {cube: <IRI>}'). It stops short of saying when NOT to use this versus adjacent siblings like search_datasets or query_lindas, so no exclusions are offered.

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