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?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: it is cursor-paginated (not a one-shot fetch), metered (rate/cost implications), and live-data (not cached/historical). It also explains the pagination workflow, going beyond the structured fields.
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?
Three short sentences, each serving a distinct purpose: what it does, how pagination works, and the metering/live-data implication. The description is front-loaded with the primary action and contains no filler or redundant information.
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 tool's simplicity (two parameters, annotations present, output schema exists), the description fully covers what an agent needs: read-only behavior (via annotations), pagination handling, and the metered/live-data constraint. Return values are already defined by the output schema, so no additional detail is necessary.
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 description coverage is 0%, so the description must carry the burden for parameters. It identifies the URL parameter as a 'TikTok video URL' and explains the cursor parameter with 'Pass the returned cursor to retrieve the next page.' Both parameters get meaningful contextual explanation, compensating for the schema's lack of descriptions.
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 opens with 'Fetch one cursor-paginated page of current comments for a TikTok video URL,' providing a specific verb (fetch), a clear resource (comments for a TikTok video), and a scoping qualifier (cursor-paginated page). This clearly differentiates from sibling tools like get_tiktok_video and list_tiktok_profile_videos, which focus on video metadata or profile feeds.
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 establishes clear context by stating it returns one page of current comments and that the returned cursor should be passed for the next page. While it does not explicitly list alternative tools, there is no other comments-related sibling tool, making the intended use unambiguous. It stops short of explicit when-not-to-use guidance.
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.
Multiple tools have unclear boundaries: `autocomplete_creators` and `search_creators` both claim the exact same example query ('Who is that fitness coach called Jane?') as their primary use case, creating direct routing conflicts. `get_creator` and `get_profile` also overlap heavily for exact platform+username lookups, with descriptions admitting the choice depends on whether 'profile metrics are the main need' — a thin distinction. `search_creators` further muddies things by dual-routing to legacy semantic search, making it a hybrid that competes with both `autocomplete_creators` and `semantic_search_creators`.
The naming follows a mostly consistent verb_noun snake_case pattern: `get_*` covers record fetching, with clear singular/batch pairs like `get_instagram_post`/`get_instagram_posts` and transcript variants. Minor deviations exist (`semantic_search_creators` prefixes a modifier, and `autocomplete_`, `find_`, `match_`, `lookup_`, `render_` each introduce different verbs), but the style is uniform and the verb typically reflects the operation type.
At 28 tools the server is heavy, but the scope is genuinely broad — three platform-specific data surfaces (Instagram, TikTok, YouTube), each requiring profile/video/transcript/listing operations, plus creator search, matching, and rendering. The count is inflated by redundancy, though: four `render_*` tools that could collapse into one parameterized tool, and batch variants of the Instagram raw-data endpoints. It is borderline acceptable for the platform-multiplied domain rather than chaotic bloat.
The tool surface covers the full read-only creator workflow: fuzzy lookup (autocomplete/search), exact profile fetch (get_profile/lookup_profiles), discovery (semantic_search/find_lookalike), fit scoring (match_creators), content evidence (get_posts), and presentation (render_*). Notable gaps include no Instagram-specific profile endpoint (odd given TikTok/YouTube have dedicated ones), no YouTube comments, and no audience-demographic data, but agents can complete realistic workflows without dead ends.