Skip to main content
Glama

TikTok comments of a video, or replies to a comment

tiktok_comments
Read-onlyIdempotent

List a TikTok video's comments in TikTok's order, up to 50 per page: text, date, likes, reply count, whether the creator liked or pinned it, language and the commenter. With comment_id, list the replies to that comment instead. First page: give url (and comment_id for replies). Next pages: give only cursor until next_cursor is null.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "tiktok_comments"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoA TikTok video or photo link (https://www.tiktok.com/@nasa/video/7695060950394703118), a short link from the app (vm.tiktok.com/…, vt.tiktok.com/…, tiktok.com/t/…) or the video id.
cursorNoThe next_cursor of the previous answer, exactly as returned, for the next page. Leave it out for the first page; with it, nothing else is needed.
comment_idNoThe id of one of the video's comments (from a previous answer), to list its replies.
include_media_urlsNoAlso return picture, video and sound file links (long links that expire after a while). Leave it off unless you need the files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive, open-world), and the description adds real behavior beyond them: result ordering ('TikTok's order'), a 50-per-page cap, the field set returned, and the fact that media links expire. It omits error behavior and rate limits, so it is strong rather than exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the primary action, then the alternate mode, then pagination rules — three short sentences with no filler. Every clause conveys an operational constraint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description enumerates the returned fields and the pagination termination signal, effectively substituting for one. For a 4-parameter, annotation-covered read tool, nothing operationally necessary is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description goes further by explaining parameter interaction — url is first-page only, cursor replaces everything else on later pages, and comment_id switches the whole operation to reply-listing. That sequencing meaning is not obvious from the per-field schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List a TikTok video's comments') plus a clearly disambiguated second mode ('With comment_id, list the replies to that comment instead'). An agent can distinguish the two behaviors from the description alone, without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit invocation rules: first page needs url (plus comment_id for replies), later pages need only cursor, and pagination continues 'until next_cursor is null.' It stops short of naming any alternative sibling tool or stating when not to use this one, so it is clear context but not full alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources