Skip to main content
Answer: “What do the measured answers use this page for, and what should our content or technical team review?”

​
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. Use get_placement_targets to discover cited pages and inspect each page’s citation metrics.
  2. Choose a returned URL and call analyze_page_performance for captured sections and citing statements.
  3. Call get_technical_features for recorded technical observations.
  4. For existing technical recommendations, use the separate HTTP recommendations route. There is no named MCP equivalent in this edition.

​
Build the handoff

Use one row per issue: page URL, observed evidence, proposed action, and what needs human review. Link back to the selected run and the answer or page evidence. Separate an existing IQRush recommendation from a new proposal made by the assistant. The page-content read retrieves captured content. It does not promise a fresh crawl or a measured score for the assistant’s proposed edit. The technical read reports observed features without proving causation. Do not manufacture a performance target from their values. This workflow prepares a handoff. It does not edit Content Playground, publish content, or run a new measurement through the external tools. Reference: page targets, page evidence, technical features.