Purchase intent often concentrates in Google Shopping before it spreads across generic web search. Source google shopping gives assistants a clean series for product and category phrases so merchandising, pricing, and retail analytics briefs cite the same JSON the API returns.
Generic web search mixes research and purchase. Shopping vertical queries lean toward comparison and checkout mindset. Giving assistants source: "google shopping" aligns recommendations with that intent layer documented in Data Sources.
E-commerce operators ask for get_growth across google shopping, amazon, and google search to see whether demand is discovery-led or transaction-led. Finance-style briefs may pair the same call with wikipedia or news volume for narrative risk.
Assistants should state that normalized scores aid comparison but do not replace inventory, margin, or conversion data from the storefront. Always pass through the dates returned in each point when summarizing.
Product marketing copy: Google Shopping trends. Broader commerce research: E-commerce product research. MCP hub: MCP trend tools for assistants.
Tools for this workflow
get_trendsTrace multi-year shopping interest for a SKU family before assortment planning.
get_trends(keyword='robot vacuum', source='google shopping', data_mode='weekly')
get_growthScore category candidates by quarter and year growth for retail decks.
get_growth(keyword='robot vacuum', source='google shopping', percent_growth=['3M', '12M', 'YTD'])
get_ranked_trendsList fast-rising shopping queries when the user asks what product themes are accelerating.
get_ranked_trends(source='google shopping', sort='yoy_pct_change', limit=30)
get_top_trendsPull Amazon best-seller feeds when the brief needs live commerce leaderboards alongside shopping search history.
get_top_trends(type='Amazon Best Sellers Top Rated', limit=20)
FAQ