List saved Costory business metrics and, optionally, matching live external metrics from connected integrations (e.g. Tsuga, BigQuery, Datadog, CloudWatch, Google Cloud Monitoring). Use when the user asks which business or integration metrics are available to query. Saved metrics return id/name/type for { type: "metric", metricId: "..." } in query. Set includeExternal: true with a specific search term to return externalMetrics with provider, integrationId, integrationName, metricName, unit, capabilities, and attributes. That catalog is enough to build { type: "externalMetric", provider, integrationId, metricName, aggregator, groupByFields, conditions } for Tsuga, Datadog (attributes are tag keys; metricName is the Datadog metric name), CloudWatch (metricName is Namespace/MetricName such as AWS/EC2/CPUUtilization; attributes are dimension names), Google Cloud Monitoring (provider "cloudmonitoring"; metricName is the metric type such as compute.googleapis.com/instance/cpu/utilization; attributes are fully-qualified group-by fields such as metric.label.state or resource.label.project_id, and conditions is an optional Monitoring filter), or Amplitude. For BigQuery or S3, the same hit also includes `schema` (typed columns: DATE / NUMERIC / STRING). Pick dateColumn from the first DATE field, metricColumn from the first NUMERIC field, and groupByFields from STRING fields (also listed in attributes). gapFillingMethod is not in the catalog — default FORWARD_FILL unless the user specifies ZERO, LINEAR_INTERPOLATION, or SPREAD. Those three fields are required on both query and a new virtual-dimension telemetry allocation. Do not call includeExternal without search; external catalogs can be large, and the tool will ask for a search term instead of listing everything. externalLimit (default 50, max 50) caps matching external results. New virtual-dimension telemetry reallocations use includeExternal + an inline `externalMetric` (same fields as a query series, plus exactly one groupByFields entry as the series key). Pass `datasourceId` only to inspect a leftover saved usage-metric datasource's `groupByDimensions` — not for new reallocations. Then call `query` (`type: "metric"`, `metricId`, `groupBy`) to inspect the values for that leftover datasource. The `datasourceId` is the same `metricsDatasource` id this tool returns as a saved-metric `id` (strip any `::metricName` suffix). Does **not** return values (use `query`).
EXAMPLES:
• "What business metrics do we have?" → {}
• "Find Tsuga metrics about requests" → { includeExternal: true, search: "request" }
• "Find BigQuery tables about revenue" → { includeExternal: true, search: "revenue" }
• "Find Datadog metrics about CPU" → { includeExternal: true, search: "cpu" }
• "Find CloudWatch metrics about CPU" → { includeExternal: true, search: "CPUUtilization" }
• "Find GCP Monitoring metrics about CPU" → { includeExternal: true, search: "cpu/utilization" } (Cloud Monitoring search matches the metric type, not its display name)
• "What live metrics can I reallocate shared cost by?" → { includeExternal: true, search: "cpu" }
• "What can I split a leftover saved-metric datasource by?" → { datasourceId: "clx…" }