List all user tables in the database together with their row counts.

Use this first to discover what data is available before describing or querying a specific table. It does not read row contents, only metadata.

Show a table's column schema, total row count and a few sample rows.

Use this after analytics_list_tables to understand a table's columns (names, types, nullability, primary keys) before writing a query.

Run a guarded, read-only SQL SELECT query with pagination.

The query is executed over a read-only connection protected by a SQLite authorizer, and is validated to be a single SELECT/WITH statement, so it cannot modify data. Results are paginated via limit/offset.

Group a table by a column and compute an aggregate — no SQL required.

A convenience workflow tool over the most common analytics pattern. Column and table names are validated against the schema, so it is safe from injection. For anything more complex, use analytics_run_query.

Load a CSV file into a SQLite table (validated via pandas).

This is the only WRITE tool. Column types are inferred by pandas. The destination table name must be a valid SQL identifier.