datadata quality check

Data Quality Check

data_quality_check

Apply read-only quality checks to CSV, JSON, JSONL, or SQLite data: duplicate keys, null thresholds, type drift, invalid emails, and optional referential gaps.

How to use data_quality_check

Provide only the required inputs below. Start with the smallest scope that answers the task, then review the risk properties before an agent executes the call.

Risk and execution properties

Read only: yes

Destructive: no

Idempotent: yes

Open world: no — operates locally or through configured services

Inputs

pathstringrequired

Local CSV, JSON, JSONL, or SQLite file.

tablestring

SQLite table name.

primary_keystring

Column to check for duplicate non-empty values.

max_null_fractionnumber

Default: 0.2

expected_typesobject

Expected type per column: string, integer, number, or boolean.

email_columnsarray

reference_pathstring

Optional local reference data source.

reference_tablestring

Reference SQLite table name.

local_keystring

reference_keystring

max_rowsinteger

Default: 10000

Example input

{
  "path": "<string>",
  "table": "<string>",
  "primary_key": "<string>",
  "max_null_fraction": 0.2,
  "expected_types": "<object>",
  "email_columns": "<array>",
  "reference_path": "<string>",
  "reference_table": "<string>",
  "local_key": "<string>",
  "reference_key": "<string>",
  "max_rows": 10000
}

Browse or search the full 74-tool reference to choose the smallest suitable capability.

Browse all tools →