Skip to main content
Glama
Crawlora MCP

Crawlora MCP

Official

tiktok_mobile_video_subtitles

Fetch a TikTok video's captions translated into a requested language and get both WebVTT text and parsed cue records for captioning or analysis.

Instructions

Video captions translated into a target language. Returns one video's own captions translated into the requested language, as TikTok's caption/language (cla) service serves them. The response carries the track twice: webvtt is the upstream WebVTT text verbatim, and cues is the same track parsed into {start_ms, end_ms, start, end, text} records so a caller does not have to implement WebVTT. video_id is the aweme id returned by the feed, search, profile-posts and hashtag endpoints. Measured 2026-10-21: the Korean-caption video 7696141388324293918 answered 11 English cues for language=en, and the same video answered Japanese, Chinese, Spanish, French, German, Korean, Portuguese, Russian, Arabic, Hindi, Indonesian, Thai, Vietnamese, Turkish and Italian tracks; a Portuguese-lyrics video answered an 18,494-character English track (240 cues). Track size is a snapshot rather than a contract (the upstream re-translates from a cache), so assert a non-empty track in the requested language, not a byte count. A video with no captions answers 400 (upstream status 5); a nonexistent video answers 500 (upstream status 4).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "video_id": "<video_id>",
      "language": "<language>"
    },
    "name": "tiktok_mobile_video_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageYesTarget language code: ar, de, en, es, fr, hi, id, it, ja, ko, pt, ru, th, tr, vi, zh
video_idYesNumeric id of the video (aweme id)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it documents the duplicated return shape, that `webvtt` is verbatim upstream text while `cues` is parsed, that track size is a snapshot rather than a contract, and the exact failure semantics (400/upstream 5 for no captions, 500/upstream 4 for a nonexistent video).

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

Conciseness4/5

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

Front-loaded with the core purpose and response shape, and every later sentence (error codes, snapshot caveat) earns its place. The measured examples (specific video ids, an 18,494-character track) are somewhat verbose, though they do substantiate the 'do not assert byte counts' warning.

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 and no annotations exist, yet the description covers return fields, parsing guarantees, upstream-status mapping, and non-determinism of track size — everything an agent needs to call it and interpret results correctly.

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, but the description adds real meaning beyond the schema: `video_id` is identified as an aweme id sourced from specific sibling endpoints, and the language set is grounded in measured behavior.

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: returns one video's own captions translated into a requested language via TikTok's `cla` service. This is unmistakable and immediately distinguishes it from feed/search/profile tools in the sibling list.

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?

Explicitly tells the caller where to obtain `video_id` (feed, search, profile-posts, hashtag endpoints) and what the error responses mean, which is clear usage context. It stops short of naming when *not* to use it versus an alternative, so it does not reach the top band.

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

Deploy Server

Other Tools