# Read GA4 ecommerce performance at item level

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

The ecommerce read: items, revenue, cart behaviour, with measurement health checked first.

**Intent.** Revenue, items and funnels from the site's own till.

## When to use

- Retail weekly reads.
- Merchandising questions.

## When not to use

- No specific contraindication beyond the preconditions below.

## Sources

Required: Google Analytics 4

## Preconditions

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

## Inputs

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

## Procedure

1. Check ecommerce measurement health first. — tools: `ga4_get_ecommerce_diagnostics`
2. Run the item and revenue reports. — tools: `ga4_run_report`

## Decision rules

- **When** Diagnostics report missing item data on purchases → **conclude** Item-level conclusions inherit the gap: bound them explicitly or fix first.

## 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

- Returns and cancellations post late or never: GA4 revenue is gross-at-event, not finance's number.

## Output

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

## Related

- Skill: [product-performance](https://www.getmcpads.com/skills/product-performance.md)
