RecipeGoogle Ads
Review Quality Score components across keywords
Quality Score components via GAQL, aggregated to where the fix lives.
IntentWhere QS is lost: expected CTR, relevance, or landing experience.
- 2
- Steps
- 2
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- CPCs drifting up at stable bids.
- Structural reviews.
Do not use it when
- Chasing QS as a goal: it is a symptom map, spend efficiency is the goal.
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.
Query QS components per keyword.
Aggregate by component and by ad group.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
One component drags across an ad group
Conclude
One fix class: copy for relevance, page for experience, both for expected CTR.
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.
- Historical QS fields differ from current: name which the table shows.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.