Documentation

get_anomalies

Pre-computed, severity-ranked metric changes with a human-readable story attached to each one.

When to use it

The "what changed" question. Run it after a deploy, after a traffic shift, or as the first call of a weekly review.

Ask for it like this

You do not name the tool. These are questions that make an assistant reach for it:

What changed on my store in the last two weeks?
Did anything break after Tuesday's theme deploy?

How to read the result

  • Each anomaly carries context about probable causes — nearby product changes, JS errors — so the story usually names the suspect.
  • Sorted by severity. Read the criticals and ignore the tail unless one matches a hypothesis you already had.

Parameters

severity
string
Filter to low, medium, high or critical.
metricType
string
Filter to bounce_rate, conversion_rate, rage_click_rate, revenue or traffic.
entityType
string
Filter to page, funnel, product or store.
limit
numberdefault: 50
Maximum anomalies to return.

Shared parameters it accepts

Documented in full on the tool reference index.

Date window — defaults to the last 30 days.

dateFrom
stringdefault: 30 days ago
Start of the window, YYYY-MM-DD. Inclusive.
dateTo
stringdefault: today
End of the window, YYYY-MM-DD. Inclusive.

Every tool also accepts merchantId, which resolves from your connection. You never pass it.

What comes back

JSON. These are the top-level keys; date-scoped tools additionally carry a _meta block with the server date and the data coverage envelope.

anomalies
Severity-ranked changes, each with the metric, the entity, the magnitude and a narrative story.

Pairs with