Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

tiktok_mobile_video_subtitles

Translate a TikTok video's captions into a chosen language and get both WebVTT text and parsed cue records for subtitles 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 with the pure-Go (device-free) signer: 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. The route is not signature-gated, so it does not need the device-backed signer. A video with no captions answers 400 (upstream status 5); a nonexistent video answers 500 (upstream status 4).

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

A4.5/5.0
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: it discloses the response shape (verbatim `webvtt` plus parsed `cues`), that the route is not signature-gated, and that track size is a per-request snapshot rather than a stable contract. The status-code mapping is exactly the kind of behavioral detail an agent needs.

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

Conciseness3/5

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

Purpose and response shape are front-loaded, but the measured evidence — a fifteen-language enumeration and a character/cue count for one example video — occupies much of the text and mostly restates that many tracks are available. Only the 'snapshot not byte count' caveat truly earns its place.

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?

There is no output schema, so the description must explain return values, and it does: it describes both the raw WebVTT field and the parsed cue record shape. Combined with error semantics and auth notes, an agent has everything needed to call and interpret it.

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 baseline is 3, but the description adds real meaning for `video_id` by naming it an aweme id obtainable from specific sibling endpoints. `language` gains little beyond the schema's enumeration, keeping this from a 5.

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 — and names the upstream service (cla) it draws from. It is clearly distinguishable from the other tiktok_mobile_* siblings, none of which return caption tracks.

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 agent where `video_id` comes from (feed, search, profile-posts, hashtag endpoints) and what each failure mode means (400 = no captions, 500 = nonexistent video). It does not explicitly exclude alternatives, but no sibling overlaps this capability.

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