> ## Documentation Index
> Fetch the complete documentation index at: https://docs.iqrush.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Read headline metrics

> Read headline metrics for the selected run.

Read headline metrics for the selected run.

**MCP tool:** `get_job_summary`. **Operation:** read. Uses the authorized connection; no project or content changes are made by this tool.

## Parameters

| Name | Type | Required | Default | Meaning and accepted values |
| - | - | - | - | - |
| `project_id` | string | Yes | `Required` | Project ID from list\_projects. Select the project in the intended workspace and environment. |
| `run_id` | string | Yes | `Required` | Run ID from list\_runs for this project. Use the exact returned value and check readiness before reading measurements. |

## Example call

Replace ID placeholders and example selections with values from your account. This is the `params` object for MCP `tools/call`.

```json theme={null}
{
  "name": "get_job_summary",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID"
  }
}
```

## Read the response

Read the top-level `metrics` object, plus `run_id`, `data_freshness`, and `data_ready`. This response has no `data` wrapper. Retain each estimate’s unit and interval; raw count fields can have a different shape from estimate objects.

### Fields to use

These selected fields explain the example and the result to preserve. Field presence depends on the response; this is not a complete response schema.

| Field | Meaning and use |
| - | - |
| `metrics.citation_share` | Headline citation-share estimate with its unit and interval. |
| `metrics.citation_coverage` | Headline citation-coverage estimate with its unit and interval. |
| `metrics.mention_count` | Raw mention count in this summary; it is not an estimate object. |
| `data_ready` | Availability of the summary data, not a statistical quality verdict. |

## Response example

Selected fields from an observed IQRush Dev response. Lists are shortened and project/run IDs are placeholders. Omitted fields remain available in the actual response.

```json theme={null}
{
  "data_ready": true,
  "metrics": {
    "citation_share": {
      "value": 0.027000000000000003,
      "unit": "proportion",
      "ci": {
        "lower": 0.019,
        "upper": 0.034,
        "level": 0.95
      },
      "n": null,
      "stability": null
    },
    "citation_coverage": {
      "value": 0.162,
      "unit": "proportion",
      "ci": {
        "lower": 0.131,
        "upper": 0.19399999999999998,
        "level": 0.95
      },
      "n": null,
      "stability": null
    },
    "mention_count": 382
  }
}
```

Read the actual returned scope, counts, and interval levels before interpreting these fields.

## Important behavior

This summary does not establish convergence. Use `get_results_stability` for the quality check. Do not relabel raw counts as response coverage.

Check tool and payload errors before using the result. [Response handling](/developers/guides/09-responses-and-metrics) explains estimates and empty results; [errors and recovery](/developers/guides/13-errors) covers invalid requests and temporary failures.

HTTP equivalent: [Read headline metrics](/developers/http/http-get-job-summary). HTTP parameters and defaults can differ.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.