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

See where Performance Max actually serves

PMax placement data read for the spend map: Search-like, Shopping, Display, YouTube shares.

IntentThe placement distribution PMax does not volunteer.

2
Steps
1
Tools
1
Rules
1
Failure modes

When to use it

Use it when

  • Monthly on PMax-heavy accounts.
  • When brand teams ask where the ads appear.

Do not use it when

  • Expecting completeness: PMax placement reporting is partial by design, and the readout says so.

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 PMax placement data.

  2. Summarise by surface and flag anything brand-inappropriate.

Decision rules

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

  • When

    Display or app placements dominate impressions while conversions sit in Search-like

    Conclude

    Impression share is not spend share: report both before anyone panics about 'display waste'.

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.

  • Placement impressions are reported without their spend: inferring cost distribution from impressions alone overstates cheap surfaces.

What the answer contains

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