# Triage Google Ads recommendations without auto-applying anything

> Tier: recipe. Operating recipe: real tool sequence, core rules, known traps.

The recommendations feed read critically: each one is a claim to verify against the account's own data, not an instruction.

**Intent.** Google's suggestions sorted into worth-it, ignore, and actively-harmful.

## When to use

- Monthly.
- When optimisation score pressure arrives from the platform or the client.

## When not to use

- Never auto-apply: several recommendation types raise spend by design.

## Sources

Required: Google Ads

## Preconditions

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

## Inputs

- `window`: Analysis window. Default: last 30 days.

## Procedure

1. Pull current recommendations with their types. — tools: `google_ads_get_recommendations`
2. For each, check the underlying claim against account data before classing it. — tools: `google_ads_get_insights`, `google_ads_get_budgets`

## Decision rules

- **When** A recommendation raises budgets or broadens targeting → **conclude** Classify as spend-expansion, not optimisation: evaluate against the efficiency target, not the optimisation score.
- **When** A recommendation fixes a real gap (disapproved ad, missing sitelink) → **conclude** Worth-it list: cheap, reversible, no spend risk.

## Evidence requirements

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

## Human approval boundary

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

## Failure modes

- Optimisation score is a platform metric, not a performance metric: reporting it as health misleads clients.

## Output

- **Readout**: The figures, with windows and accounts named.
- **Flags**: What deserves a deeper skill or a human decision.