Profile the columns of an open-data dataset
describe_dataset_columnsFetches 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
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Dataset ID (slug): the 'id' of a search_datasets hit | |
| lang | No | Language for titles/descriptions: de, fr, it or en (default en; falls back to de) | |
| format | No | Preferred resource format (overrides the CSV-first default) | |
| portal | No | Catalogue: '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) | |
| examples | No | Distinct example values per column (default 5) | |
| resource | No | Optional resource selector: 0-based index from get_dataset, resource id, or part of its title. Default: best CSV > JSON > GeoJSON | |
| resource_url | No | Alternatively, 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' |