Search TikTok videos by keyword, returning matching posts with stats. Use for topic/trend discovery and competitive research. Paginate with cursor.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of items to return, <=30 | |
| cursor | No | Pagination cursor — pass the `cursor`/`max_cursor`/`has_more` value from a prior response. | |
| expand | No | Return the full untrimmed payload. Default false = compact JSON. | |
| keyword | Yes | Search query text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It states it searches and returns posts with stats, but lacks information on rate limits, authentication requirements, data recency, or any side effects. The read-only nature is implied but not explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences, each adding value. It front-loads the verb and resource, and avoids redundancy. Minor improvement could be to structure usage guidelines and behavioral notes separately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description partially compensates by mentioning 'posts with stats,' but it does not explain the structure of results or error behavior. For a tool with 4 parameters and many siblings, more detail on return values would enhance completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds extra context by reinforcing pagination with `cursor` and mentioning use cases. However, it does not provide deeper semantics beyond what the schema already offers, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches TikTok videos by keyword and returns matching posts with stats. The name and description distinguish it from sibling search tools (e.g., tiktok_search_creators), though no explicit differentiation is given.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides usage context (topic/trend discovery, competitive research) and mentions pagination with cursor. However, it does not specify when not to use this tool or mention alternative search tools for other resource types.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct data type or action (creator, video, comment, sound, hashtag, search, etc.) with no functional overlap. Agents can easily distinguish them based on their clear entity-action pairing.
All tools follow a 'tiktok_' prefix and a consistent noun-first pattern (e.g., 'tiktok_creator_profile', 'tiktok_video_stats'), but there is a minor inconsistency between 'creator' and 'user' for the same entity (e.g., 'tiktok_user_stories' vs 'tiktok_creator_profile').
At 19 tools, the count is slightly high but justified by the breadth of TikTok's public data surface (profiles, videos, comments, sounds, hashtags, searches, etc.). Each tool serves a specific purpose, and the set feels comprehensive rather than bloated.
The tool set covers most read-only operations for TikTok public data, including profiles, videos, comments, sounds, hashtags, and searches. Missing are direct trending feeds or aggregated analytics, but search capabilities compensate. No create/update/delete exists, which is expected for a data extraction server.