I'll systematically check for data quality issues across the key columns in this dataset. {"action": "tool_call", "reasoning": "First, I'll examine salary data for outliers and consistency. I'll check the distribution of salary_usd, look for any impossible values (negatives, zeros), and verify if salary_currency affects the USD conversion appropriately.", "tool": "query_sql", "args": {"sql": "SELECT MIN(salary_usd) as min_salary, MAX(salary_usd) as max_salary, AVG(salary_usd) as avg_salary, MEDIAN(salary_usd) as median_salary, STDDEV(salary_usd) as stddev_salary, COUNT(*) as total_count, COUNT(CASE WHEN salary_usd < 30000 THEN 1 END) as very_low_count, COUNT(CASE WHEN salary_usd > 300000 THEN 1 END) as very_high_count FROM raw.ai_job_dataset", "purpose": "Check salary distribution for outliers and impossible values", "source": "raw"}}