delimit_obs_metrics
Fetch numeric metric series from your observability backend for a given time range. Use during runtime health analysis to correlate with log data.
Instructions
Pull numeric metric series from the observability backend (Pro).
When to use: during runtime health investigation when you need numeric series (CPU, memory, request rate, error rate, latency percentiles) over a named time window. Pair with delimit_obs_logs to correlate a numeric anomaly with the underlying log lines. When NOT to use: for free-text search of log lines (use delimit_obs_logs), to read or configure alert rules (delimit_obs_alerts), or for a quick at-a-glance health rollup (delimit_obs_status).
Sibling contrast: delimit_obs_logs returns text matches; this returns numeric time series. delimit_obs_status is the rollup-summary surface; this is the raw-series surface. delimit_obs_alerts configures thresholds against these same series.
Side effects: read-only on the metrics backend and gated by require_premium — unlicensed callers receive a license payload and no query runs. On a licensed call, invokes backends.tools_infra.obs_metrics which queries the backing metrics store; no data is written, no ledger entry, no notification. The response is routed through _with_next_steps.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Metric query name. Default "system" (general system metrics). Backend-specific values supported. | system |
| time_range | No | Window like "1h", "24h", "7d". Default "1h". | 1h |
| source | No | Optional data source override. Default None = backend default source. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||