Compare one domain

Compare one domain’s citation share or count across two runs or two conditions. MCP tool: get_paired_contrast. 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 for a within-run comparison. For the documented cross-run request, set it to run_id_b and also supply run_id_a and run_id_b.
`entity_or_domain`	string	Yes	`Required`	Bare cited domain to compare. This operation supports citation analysis; a brand name or full page URL is not a substitute for the domain.
`score_family`	string	No	`'citation'`	Use citation; other score families are not supported by this operation in this edition.
`metric`	string	No	`'share'`	share compares citation share; count compares citation counts. Only the citation family is supported.
`condition_a`	object or string or null	No	`null`	First within-run selection, using measured platform, topic, intent, or prompt_type values. Send an object or its JSON-encoded string.
`condition_b`	object or string or null	No	`null`	Second within-run selection, using the same condition format as condition_a. Use run_id_a and run_id_b instead for a cross-run comparison.
`run_id_a`	string or null	No	`null`	Reference run from the selected project. Supply together with run_id_b for a cross-run comparison.
`run_id_b`	string or null	No	`null`	Checkpoint run from the selected project. The reported difference is B minus A.
`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.
`filters`	object or string or null	No	`null`	JSON-encoded filter array string. Use dimension and values objects inside the array; this argument does not accept a native array in this edition.

Example call

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

{
  "name": "get_paired_contrast",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "NEWER_RUN_ID",
    "entity_or_domain": "colorescience.com",
    "score_family": "citation",
    "metric": "share",
    "run_id_a": "OLDER_RUN_ID",
    "run_id_b": "NEWER_RUN_ID"
  }
}

Read the response

Read data.contrast.value_a, value_b, diff, ci_diff, significant, and correction. diff is B minus A.

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.entity_or_domain`	Domain being compared.
`data.contrast.value_a`	Value for condition A or run A.
`data.contrast.value_b`	Value for condition B or run B.
`data.contrast.diff`	B minus A, in the selected metric’s scale.
`data.contrast.ci_diff`	Lower bound, upper bound, and confidence level for the difference.
`data.contrast.significant`	Returned significance result; retain it with the difference interval.

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.

{
  "data_ready": true,
  "data": {
    "score_family": "citation",
    "metric": "share",
    "entity_or_domain": "colorescience.com",
    "contrast": {
      "value_a": 0.0335164004223577,
      "value_b": 0.026726239624239412,
      "diff": -0.006790160798118287,
      "ci_diff": {
        "lower": -0.019421924882329574,
        "upper": 0.00255965226798446,
        "level": 0.95
      },
      "significant": false
    }
  }
}

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

Important behavior

Only domain-level citation share/count is supported. For cross-run calls set run_id to run_id_b; for within-run calls use condition objects. Null difference fields mean the comparison is unavailable. Encode a filter array as a JSON string for this tool. Check tool and payload errors before using the result. Response handling explains estimates and empty results; errors and recovery covers invalid requests and temporary failures. HTTP equivalent: Compare one domain. HTTP parameters and defaults can differ.

Get started

Connect securely

Read measurements

Build dependable integrations

Build reports

Report recipes

Reference

Session and discovery

Visibility measurements

Sources and evidence

Changes and trends

Google data

Pages and report planning

HTTP operations

Compare one domain

Parameters

Example call

Read the response

Fields to use

Response example

Important behavior

​Parameters

​Example call

​Read the response

​Fields to use

​Response example

​Important behavior

Parameters

Example call

Read the response

Fields to use

Response example

Important behavior