Skip to content
Get MCP AdsGet MCP Ads, home
Start free
RecipeGoogle Ads

Read Google Shopping performance by product

Shopping performance joined to product statuses, so the readout names products, not IDs.

IntentProduct-level Shopping truth: what serves, what sells, what silently sits.

2
Steps
2
Tools
2
Rules
1
Failure modes

When to use it

Use it when

  • Weekly on retail accounts.
  • Before and after feed pushes.

Do not use it when

  • Judging brand-new products: they need impressions before efficiency means anything.

What it needs first

Required

Preconditions

  • The account is ticked in the dashboard, confirmed via list_accounts.

Inputs

window
Analysis window.Default: last 30 days.

Procedure

In order. Every tool named is one the gateway ships, and links to its reference.

  1. Pull Shopping performance by product.

  2. Join product statuses and attributes.

Decision rules

The observable condition, what it lets you conclude, and what takes the conclusion back.

  • When

    A product has impressions and no clicks at scale

    Conclude

    Price or image problem in the SERP, not a bidding problem.

  • When

    Top sellers by site revenue barely serve

    Conclude

    Feed or priority issue: the campaign starves the winners; escalate to shopping-feed-health.

Evidence every conclusion must carry

  • Every figure carries its account, metric and window.
  • Anything below a readable sample size is reported as unjudged, not as zero.

Where the agent stops

  • The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.

How it goes wrong quietly

The cases where the analysis is wrong and still looks right. Read them before trusting a number.

  • Aggregating across product partitions hides the losers inside 'everything else'.

What the answer contains

01Readout
The figures, with windows and accounts named.
02Flags
What deserves a deeper skill or a human decision.