Skip to main content
Answer: “Which of our product detail pages are cited, and what do the answers use them to support?”

​
Prepare the scope

Use list_projects and list_runs to choose the project and completed run. Check readiness, then call get_results_stability for the same run and supported filters. For each measurement, preserve the scope, returned confidence interval, and row-quality fields. See run selection and decision-grade measurement. The JSON examples below are MCP tools/call parameter objects. Replace ID placeholders and sample selections with values discovered in your account.

​
Retrieve the evidence

  1. Read owned URL citation coverage.
  2. Review the returned URLs to identify actual product detail pages. A collection, category, or editorial page is a different page type.
  3. Pass a returned product-page URL to analyze_page_performance and get_technical_features.

​
Build the report

Create a table with product-page URL, citation coverage and interval, supporting answer statements, and available technical observations. Keep proposed page edits in a separate column from measured findings. When captured content is unavailable, state that limit. Do not describe absent content as weak content. Technical features describe pages that were cited; they do not establish feature targets or prove why those pages were cited.

​
Add referral or product activity when available

Check list_ga4_properties first. If the project has usable linked data, get_ai_traffic_performance, get_ecommerce_funnel, and get_product_performance can add the stored referral and commerce context. Keep their resolved snapshot window with the result. Citation visibility and Google referral activity are separate measurements. Do not infer a sale, conversion, or revenue amount from a citation. An empty product list does not establish zero product visibility. Reference: citation scores, page evidence, Google data.