List TikTok profile videos
tiktok_profile_videos_listList videos from a TikTok profile by handle. Credits: 1 base; hostMedia=true adds +2 per hosted asset (up to 24 / 49 max). Failed assets are not surcharged.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Alias for `sortBy`. Prefer `sortBy`. | |
| trim | No | Optional flag for a smaller response with fewer fields. | |
| urls | No | Alias for `handle`. Prefer `handle`. | |
| user | No | Alias for `handle`. Prefer `handle`. | |
| limit | No | Ignored if this tool does not support it. | |
| cursor | No | Pagination cursor returned by a previous response. | |
| handle | No | TikTok handle whose videos should be listed. | |
| offset | No | Ignored if this tool does not support it. | |
| region | No | Optional ISO 3166-1 country code for the request. | |
| sortBy | No | Optional sort order for the returned TikTok videos. | |
| userId | No | Optional TikTok user id to speed up the request. | |
| context | Yes | Describe the user's underlying goal in one sentence — not the tool you are calling. | |
| pageSize | No | Ignored if this tool does not support it. | |
| userName | No | Alias for `handle`. Prefer `handle`. | |
| username | No | Alias for `handle`. Prefer `handle`. | |
| hostMedia | No | When true, hosts source media for 90 days and returns delivery URLs in each video's `hostedMedia`. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. | |
| maxResults | No | Ignored if this tool does not support it. | |
| profileUrl | No | Alias for `handle`. Prefer `handle`. | |
| linkedinUrl | No | Alias for `handle`. Prefer `handle`. | |
| max_results | No | Ignored if this tool does not support it. | |
| screen_name | No | Alias for `handle`. Prefer `handle`. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. |