Skip to main content
Glama

Profile the columns of an open-data dataset

describe_dataset_columns
Read-only

Fetches a dataset's CSV/JSON/GeoJSON resource and returns row count plus per-column types, non-null counts and examples so you can plan query filters or aggregate group-bys.

Instructions

Fetch and parse a dataset's best CSV/JSON/GeoJSON resource (or a direct resource_url) and return its row count and, per column, the detected type (number/string/mixed), non-null count and example values; use it to plan query_dataset filters or aggregate_dataset group-bys. Examples: {id: ''} or {id: '', portal: 'stadt-zuerich', resource: '1'}.

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": "describe_dataset_columns"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoDataset ID (slug): the 'id' of a search_datasets hit
langNoLanguage for titles/descriptions: de, fr, it or en (default en; falls back to de)
formatNoPreferred resource format (overrides the CSV-first default)
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)
examplesNoDistinct example values per column (default 5)
resourceNoOptional resource selector: 0-based index from get_dataset, resource id, or part of its title. Default: best CSV > JSON > GeoJSON
resource_urlNoAlternatively, a direct https URL of a CSV/JSON/GeoJSON file (e.g. a download_url from get_dataset). May be disabled on public deployments, prefer 'id'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the burden of explaining the response contract, and it does: row count plus per-column type, non-null count and example values. It does not cover failure modes for large or unparseable resources, or the cost of fetching a full file, which would matter for an open-world fetch tool.

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 behavior and its purpose are front-loaded in the first clause, and the two example invocations at the end are compact and practical. The single semicolon-chained sentence is dense, though every clause contributes information.

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?

With no output schema, a 7-parameter surface and full schema coverage, the description fills the critical gap by specifying the return payload and the downstream use case, and the examples demonstrate invocation. It is only slightly incomplete on operational behavior such as handling of very large resources or parse failures.

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 100%, so every parameter (id, lang, format, portal, examples, resource, resource_url) is already documented in the schema. The two inline call examples show realistic parameter combinations, which is useful, but the description adds no new semantics about individual parameters beyond what the schema states.

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?

"Fetch and parse a dataset's best CSV/JSON/GeoJSON resource ... and return its row count and, per column, the detected type, non-null count and example values" gives a specific verb, a specific resource, and the exact output shape. It further distinguishes itself from siblings by naming query_dataset and aggregate_dataset as the downstream consumers of this profiler.

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?

The clause "use it to plan query_dataset filters or aggregate_dataset group-bys" tells the agent exactly what this tool is for relative to its closest siblings. There is no explicit when-not (e.g. 'do not use this to retrieve actual rows, use query_dataset'), so it stops short of full routing guidance.

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