describe_dataset

Return a dataset’s schema and row count plus a small head sample. Use this before writing a query_datasets SQL to confirm column names and types.

When to use it

• “What columns are in this dataset?”
• Before slicing or filtering a dataset for the first time.

Inputs

Parameter	Type	Required	Description
dataset_id	string	Yes	The ds_... identifier returned by a previous tool.
sample_rows	integer	No	Preview row count. Default 5, max 20.
target_tenant_id	string	No	Super tenants only.

Returns

JSON with the dataset handle, schema (columns + inferred types), row count, and a head sample.

Notes

• The sample is capped at 20 rows. Anything beyond that should flow through query_datasets with an explicit LIMIT.