> ## 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.

# Find changes to investigate

> Collect candidate citation-share and rank changes for follow-up.

Collect candidate citation-share and rank changes for follow-up.

**MCP tool:** `get_significant_findings`. **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. |
| `kinds` | string\[] or null | No | `null` | Selected finding kinds: share\_change and/or rank\_displacement. |
| `min_effect_size` | number | No | `0.0` | Minimum absolute effect included in the findings selection; not a promise of business importance. |
| `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": "get_significant_findings",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "reference": {
      "type": "previous_run"
    },
    "kinds": [
      "share_change"
    ]
  }
}
```

## Read the response

Read `data.findings`, `data.reference_run_id`, and `data.reference_type`. Up to 50 findings include kind, subject, contrast, scope, and correction metadata. `correction.method` is `none` in this edition and `family_size` records the comparison family.

### 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.kinds` | Finding types requested for selection. |
| `data.findings[].kind` | Type of this finding, such as share\_change. |
| `data.findings[].subject.domain` | Source associated with this finding. |
| `data.findings[].contrast` | Reference/checkpoint comparison with its difference and uncertainty. Read the kind before labeling the units. |

## 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": {
    "kinds": [
      "share_change"
    ],
    "findings": [
      {
        "kind": "share_change",
        "subject": {
          "domain": "aad.org"
        },
        "contrast": {
          "value_a": 0.18162866582649265,
          "value_b": 0.15411077594718775,
          "diff": -0.027517889879304896,
          "ci_diff": {
            "lower": -0.049268835714634585,
            "upper": -0.0005404802297687744,
            "level": 0.95
          },
          "significant": true
        }
      }
    ]
  }
}
```

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

## Important behavior

These are exploratory candidates, not a set of confirmed changes. Broad screening increases chance findings. Use a specific follow-up question and retain the comparison limitations.

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: [Find changes to investigate](/developers/http/http-get-significant-findings). HTTP parameters and defaults can differ.


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