RecipeTikTok Ads
Run a raw TikTok report for a bespoke question
The raw reporting endpoint, validated then run: TikTok's escape hatch.
IntentThe exact table the packaged reads do not provide.
- 2
- Steps
- 3
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- Bespoke dimensions or metrics.
- Async heavy pulls.
Do not use it when
- When a packaged tool answers it already.
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.
Validate the query shape.
Run the report, async when the window is wide.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
The window exceeds sync limits
Conclude
Go async and poll: a truncated sync read is silent data loss.
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.
- Metric availability varies by dimension combination: validation exists because the API's own errors arrive late.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.