> ## 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.

# Screen for citation drift

> Check how the citation landscape differs from a reference run.

Check how the citation landscape differs from a reference run.

**MCP tool:** `screen_drift`. **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. |
| `reference` | string or object or null | No | `null` | Choose the comparison run: previous\_run, first\_run, or specific\_run. For specific\_run, include run\_id. The request’s run\_id is the checkpoint. |
| `aggregation_level` | string | No | `'domain'` | domain requests source-domain results; url requests individual-page results. Keep the same reporting unit when comparing measurements. |
| `threshold` | number | No | `Omit for standard use` | Optional advanced drift-screen control. Omit for standard reporting; it is not the convergence SNR target. |
| `n_boot` | integer | No | `Omit for standard use` | Optional advanced analysis control. Omit for standard reporting; use the advertised runtime schema if an integration requires it. |
| `group_by` | string\[] or null | No | `null` | Split results into rows by the requested dimensions. Check both filters\_applied.group\_by and each row’s group\_by\_values before labeling the groups. |
| `filters` | object\[] or null | No | `null` | Select measured answers with objects containing dimension and values. Use labels from list\_dimension\_options; inspect returned warnings for filters that were not applied. |

## 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": "screen_drift",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "reference": {
      "type": "previous_run"
    },
    "aggregation_level": "domain"
  }
}
```

## Read the response

Returns landscape comparison data and the reference/checkpoint context. Inspect availability, warnings, and comparison fields rather than interpreting a single correlation as proof of change.

### 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 |
| - | - |
| `data.reference_type` | Rule used to choose the reference run. |
| `data.rows[].is_drift_detected` | Returned comparison verdict; interpret together with sufficiency and warnings. |
| `data.rows[].is_sufficient` | Whether this comparison has sufficient evidence for the reported assessment. |
| `data.rows[].insufficient_reason` | Explanation when sufficient evidence is not available; null when no reason is supplied. |
| `data.rows[].n_domains_compared` | Number of source entries included in the comparison’s scope. |

## 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,
  "data": {
    "reference_type": "previous_run",
    "aggregation_level": "domain",
    "rows": [
      {
        "is_drift_detected": true,
        "is_sufficient": true,
        "insufficient_reason": null,
        "n_domains_compared": 175
      }
    ]
  }
}
```

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

## Important behavior

Use for cross-run comparison. `rank_correlation_resample_spread`, when supplied, is a descriptive range and not a confidence interval on the point correlation. Leave advanced analysis controls at their defaults.

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: [Screen for citation drift](/developers/http/http-screen-drift). HTTP parameters and defaults can differ.


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