I need to find which columns have missing values and calculate the percentage missing for each. Let me start by querying the column metadata to get null counts across all tables. ```json { "action": "tool_call", "reasoning": "The analytics.column_overview metadata table contains null_count for every column. I'll query it to find all columns with null_count > 0, calculate the missing percentage using the row counts from analytics.table_overview, and order by missing percentage to show the most problematic columns first.", "tool": "query_sql", "args": { "sql": "SELECT co.table_name, co.column_name, co.null_count, tov.row_count, ROUND(100.0 * co.null_count / NULLIF(tov.row_count, 0), 2) AS missing_pct FROM analytics.column_overview co JOIN analytics.table_overview tov ON co.table_name = tov.table_name WHERE co.null_count > 0 ORDER BY missing_pct DESC, co.null_count DESC", "purpose": "Find all columns with missing values and calculate the percentage missing in each", "source": "raw" } } ```