> ## 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 page content evidence

> Retrieve captured page sections and the answer statements citing the page.

Retrieve captured page sections and the answer statements citing the page.

**MCP tool:** `analyze_page_performance`. **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. |
| `url` | string | Yes | `Required` | Page URL or domain to inspect in this run. Prefer the exact cited URL when requesting evidence for a particular page. |

## 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": "analyze_page_performance",
  "arguments": {
    "project_id": "PROJECT_ID",
    "run_id": "RUN_ID",
    "url": "https://www.colorescience.com/collections/mineral-sunscreens"
  }
}
```

## Read the response

Read `data.chunks`, `statements`, `chunks_source`, `n_chunks`, and `n_statements`.

### 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.url` | URL being inspected for page evidence. |
| `data.n_chunks` | Number of page sections returned in the complete response. |
| `data.n_statements` | Number of supporting statement records returned in the complete response. |
| `data.chunks[].chunk_index` | Page-section index used to identify a returned chunk. |
| `data.chunks[].title` | Captured section title, which can be empty. |
| `data.chunks[].is_true_citation` | Returned flag distinguishing cited sections from other captured sections; retain the flag with the evidence. |

## 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": {
    "url": "https://www.colorescience.com/collections/mineral-sunscreens",
    "n_chunks": 15,
    "n_statements": 518,
    "chunks": [
      {
        "chunk_index": 0,
        "title": "",
        "is_true_citation": true
      }
    ]
  }
}
```

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

## Important behavior

A section-level assessment is possible only when page content exists. This read does not promise a fresh crawl or produce an independently measured content score.

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 page content evidence](/developers/http/http-analyze-page-performance). HTTP parameters and defaults can differ.


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