平易な言葉での質問を SQL に変換し、検査して改善できるようにします

SELECT
  "data.tool_name" AS tool_name,
  "data.args.operation" AS operation,
  COUNT(*) AS calls,
  SUM(CASE
    WHEN "data.status" = 'failed' THEN 1 ELSE 0
  END) AS failures,
  100.0 * SUM(CASE
    WHEN "data.status" = 'failed' THEN 1 ELSE 0
  END) / NULLIF(COUNT(*), 0) AS failure_rate_pct,
  approx_percentile_cont("data.latency_ms", 0.95) AS p95_latency_ms
FROM agent_events
WHERE event_name = 'agent_tool_called'
  AND timestamp_utc >= now() - INTERVAL '7 days'
GROUP BY "data.tool_name", "data.args.operation"
HAVING COUNT(*) >= 20
ORDER BY failure_rate_pct DESC, calls DESC;