RecipeTikTok Ads
Probe raw TikTok entities when packaged reads fall short
The raw entities endpoint for edge-case fields, used sparingly and cited precisely.
IntentDirect entity access for fields the packaged tools do not surface.
- 2
- Steps
- 2
- Tools
- 1
- Rules
- 1
- Failure modes
When to use it
Use it when
- A field exists in the API but not in packaged reads.
Do not use it when
- Routine reads: packaged tools carry the conventions and the safety.
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.
Probe the entity with the exact fields needed.
Cross-check one packaged read to anchor interpretation.
Decision rules
The observable condition, what it lets you conclude, and what takes the conclusion back.
When
Raw and packaged disagree
Conclude
Trust neither yet: name the field and verify against the UI before concluding.
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.
- Raw fields change with API versions: pin the version in the finding.
What the answer contains
- 01Readout
- The figures, with windows and accounts named.
- 02Flags
- What deserves a deeper skill or a human decision.