Weekly SEO Report

Produce a concise weekly SEO performance digest for one Search Console property, using the GSC Wizard MCP tools. The user's request may contain a property (a GSC site URL or a recognizable site name) and/or a focus hint (a market, a site section, a topic); use it to resolve the property and to slant the analysis.

Steps

1. Resolve the property. If the user (or the request) named a property, use it. Otherwise call list_sites first. Site URLs use GSC formats: sc-domain:example.com or https://www.example.com/. If several plausible matches exist, ask the user which one before continuing.

2. Compute the date windows. GSC data lags about 2 to 3 days, so offset the report week back by 3 days:

   • Current week: today - 9 through today - 3 (7 days inclusive).
   • Prior week: today - 16 through today - 10. Use these exact windows in every dated call so all sections line up. If the user asks for a specific range, honor it, but keep the newest 2 days out of any window and say why. When presenting results, state the actual dates covered; do not imply the digest runs through today.

3. Headline metrics. Call get_site_summary with days: 7. This tool applies the same 3-day lag offset internally and returns a same-length prior-period comparison, so its window matches step 2. Report clicks, impressions, CTR, and average position with week-over-week change. ctr values are already percentages on a 0-100 scale; never multiply them by 100. Position: lower is better; a change toward a lower number is an improvement.

4. Top query and page movers. query_top_queries and query_top_pages take a single date range with no comparison parameter, so call each tool twice: once with the current week's startDate/endDate and once with the prior week's (use limit: 50). Join rows by query (or page), compute click and position deltas, and keep the largest gainers and largest decliners in each dimension.

5. Ranking movement. Call get_ranking_changes with startDate/endDate set to the current week, comparisonStartDate/comparisonEndDate set to the prior week, and dimension: "query". If step 4 showed the movement is page-driven, call it again with dimension: "page". Highlight notable entries from all four buckets: new, lost, improved, declined.