data_stats
Summarize observation coverage and catalog health with aggregate counts or filtered per-concept details on stored rows, gaps, stale data, and source stores.
Instructions
Observation coverage: a fast aggregate summary, or per-concept detail.
Default (no arguments): an aggregate summary — total_concepts
(catalog size), covered_concepts (routable and crawled, the same
figure coverage_report reports), concepts_with_observations
(raw distinct concepts holding rows), total_stored_rows,
gap_concepts / stale_concepts, and a per-entity-type rollup —
plus a stores section from the latest data census (local master
exact + each shard's catalog-based estimate, chunk count, data
time-range end). total_stored_rows counts stored ROWS: sources
coexist per point, so two sources on one point count twice; the
per-concept listing below counts distinct observation points instead.
The per-concept listing (point count, latest date, distinct sources,
most recent fetch) is returned only when narrowed — pass concept_id
or entity_type for a filtered listing, or detail=True for the
unfiltered one. That listing sweeps the observations table and is
deliberately not the default.
Read-only: census rows are READ, never collected (refresh via the panel
action or the census CLI). The same data powers the panel's
/panel/data page.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "data_stats"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| detail | No | Return the full per-concept listing even without filters. | |
| concept_id | No | Restrict the per-concept listing to one concept. | |
| entity_type | No | Restrict the per-concept listing to one entity type. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||