# Read Meta ad-level performance with creative names

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

Ad performance with the creative behind each ad, the table creative discussions should start from.

**Intent.** Ad-level results joined to their creatives, so findings name assets.

## When to use

- Creative reviews.
- Before pausing 'the bad ads'.

## When not to use

- Below ~1,000 impressions per ad: rank, do not judge.

## Sources

Required: Meta Ads

## Preconditions

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

## Inputs

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

## Procedure

1. Pull ads with their creative links. — tools: `meta_get_ads`
2. Join creatives and performance. — tools: `meta_get_creatives`, `meta_get_insights`

## Decision rules

- **When** The same creative runs in several ads → **conclude** Aggregate by creative before ranking: the asset is the unit, not the ad ID.

## 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

- Dynamic and Advantage+ formats assemble variants: the 'creative' is a recipe, and variant-level truth is partial.

## Output

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

## Related

- Skill: [creative-fatigue](https://www.getmcpads.com/skills/creative-fatigue.md)