list_tiktok_video_commentsFetch one cursor-paginated page of current comments for a TikTok video URL.
Pass the returned cursor to retrieve the next page. This is a metered live-data request.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| cursor | No |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | No | ||
| data | No | ||
| count | No | ||
| results | No | ||
| has_more | No | ||
| not_found | No | ||
| next_cursor | No | ||
| suggested_followups | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds valuable behavioral context beyond the annotations: it discloses cursor-based pagination, that each call returns one page only, and that the request is metered and live-data. These details inform the agent about cost and usage patterns, which the readOnlyHint and openWorldHint annotations do not cover.
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 extremely concise and front-loaded, with two sentences that each carry important information. No filler or repetition of schema details; every phrase adds value.
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 presence of an output schema and safety annotations, the description sufficiently covers the tool's purpose, pagination mechanics, and metered nature. No critical gaps remain for a paginated list operation.
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?
With 0% schema description coverage, the description compensates by explaining the url parameter as a TikTok video URL and the cursor parameter as the returned value to pass for the next page. It does not explicitly name the parameters but clearly maps the concepts to the schema.
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 identifies the tool as fetching one cursor-paginated page of current comments for a TikTok video URL. The verb 'Fetch' plus specific resource 'comments for a TikTok video' unambiguously distinguishes it from sibling tools like get_tiktok_video or list_tiktok_profile_videos.
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 gives clear context on how to use the tool, specifically instructing to pass the returned cursor to retrieve the next page and noting it is a metered live-data request. It does not explicitly state when not to use it or mention alternatives, but the intended use case is clearly implied.
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.
Several tools have overlapping boundaries: autocomplete_creators and search_creators are described as near-equivalent fuzzy lookups, get_creator and get_profile both resolve exact platform+username input, and the Instagram/TikTok post helpers overlap with generic get_posts. The descriptions work hard to disambiguate, but an agent would frequently need to choose between two or three equally plausible tools.
Most tools follow a clear verb_noun snake_case pattern, such as get_youtube_video, search_creators, match_creators, and render_creator_profile. Minor inconsistencies exist: singular/plural variants (get_instagram_post vs get_instagram_posts), list_ vs get_ for video listing, and search_creators carrying legacy semantic behavior under a lookup-sounding name.
Twenty-eight tools places the server in the 'too many' range, and the count is inflated by near-duplicates like autocomplete_creators/search_creators, get_creator/get_profile, and singular/batch transcript variants. Even with three social platforms and rendering helpers, the surface would be more focused around 18–22 tools.
The core influencer research workflow is well covered: handle resolution, batch lookup, semantic discovery, lookalikes, posts, transcripts, YouTube search, matching, and comparison rendering. Gaps are minor—there is no creator shortlist persistence or cross-platform comment support—but the main discovery-to-match path has no dead ends.