Skip to content
Get MCP AdsGet MCP Ads, home
Start free
View as Markdown
RecipeMeta Ads

List Meta studies and what they settled

Ad studies listed with their status, the institutional memory read before designing the next test.

IntentThe account's experiment history: what was tested, what concluded.

2
Steps
2
Tools
1
Rules
1
Failure modes

When to use it

Use it when

  • Before proposing a test someone already ran.
  • Building the learning log.

Do not use it when

  • No specific contraindication beyond the preconditions below.

What it needs first

Required

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. List studies with dates and cells.

  2. Pull results for the concluded ones that matter.

Decision rules

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

  • When

    A proposed test duplicates a concluded one

    Conclude

    Read the old result first: rerunning is only justified if conditions changed materially.

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.

  • Old studies measured old creative and old auctions: expiry applies to learnings too.

What the answer contains

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