{
    "action": "tool_call",
    "reasoning": "The earlier draft cited numbers I can't see in the current evidence, so I'm re-grounding it. First I'll look at the raw Amount text formats across all five monthly tables, to see how to clean them before ranking.",
    "tool": "query_sql",
    "args": {
        "sql": "WITH u AS (SELECT 'Jan' AS m, \"Company Name\" AS company, Amount, Stage, Sector FROM raw.\"Indian Startups _ Funding  Investors Data January 2022\" UNION ALL SELECT 'Feb', \"Company Name\", Amount, Stage, Sector FROM raw.\"Indian Startups _ Funding  Investors Data February 2022\" UNION ALL SELECT 'Mar', \"Company Name\", Amount, Stage, Sector FROM raw.\"Indian Startups _ Funding  Investors Data March 2022\" UNION ALL SELECT 'Apr', \"Company Name\", Amount, Stage, Sector FROM raw.\"Indian Startups _ Funding  Investors Data April 2022\" UNION ALL SELECT 'May', \"Company Name\", Amount, Stage, Sector FROM raw.\"Indian Startups _ Funding  Investors Data May 2022\") SELECT m, COUNT(*) AS n_rows, COUNT(Amount) AS n_amount, COUNT(*) FILTER (WHERE Amount LIKE '$%') AS n_dollar, COUNT(*) FILTER (WHERE Amount IS NOT NULL AND Amount NOT LIKE '$%') AS n_other, MIN(Amount) AS min_txt, MAX(Amount) AS max_txt FROM u GROUP BY m ORDER BY m",
        "purpose": "Profile the text format of Amount across all five monthly tables",
        "source": "raw"
    }
}