Skip to content
Get MCP AdsGet MCP Ads, home
Start free
Recipe

Sweep change histories across platforms for a period

Change events from every platform that keeps them, merged into one dated timeline.

IntentEverything humans and systems changed, everywhere, in one timeline.

2
Steps
2
Tools
1
Rules
1
Failure modes

When to use it

Use it when

  • Post-mortems.
  • Handover weeks.
  • Before/after big performance moves.

Do not use it when

  • No specific contraindication beyond the preconditions below.

What it needs first

No single source is required: this one reads across whatever you have connected.

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. Pull change histories where platforms expose them.

  2. Merge into one timeline, timezone-aligned.

Decision rules

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

  • When

    Platforms without change logs (TikTok, Pinterest) are in scope

    Conclude

    Say the timeline is partial by platform, not complete: absence of a log is not absence of changes.

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.

  • Timezone misalignment shuffles cause and effect across midnight: align before reading.

What the answer contains

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