Skip to content
Get MCP AdsGet MCP Ads, home
Start free
RecipeSearch Console

Compare Web, Image, Video and News search performance

The per-surface comparison: Web against Image against Video, with the surprises named.

IntentWhich search surfaces carry the site, and which are untapped.

2
Steps
1
Tools
1
Rules
1
Failure modes

When to use it

Use it when

  • Quarterly.
  • Visual-inventory sites wondering about Image.

Do not use it when

  • No specific contraindication beyond the preconditions below.

What it needs first

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. Compare search types over the window.

  2. Rank surfaces by clicks and note anomalies.

Decision rules

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

  • When

    Image search carries real clicks for a commerce site

    Conclude

    Image optimisation is a channel, not a chore: size it.

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.

  • Surfaces have different freshness lags: compare like windows.

What the answer contains

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