Skip to main content
Glama

Add animated subtitles

add_subtitles

Transcribes the speech of a video and burns stylish, animated subtitles into it (word-by-word highlight like on TikTok/Reels). Can add a second, translated line. Uses the user's Klipa credits like on the website. 11 styles, shown as pictures by show_subtitle_styles.

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": "add_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNoSubtitle style: net (clean), carte (text on a card), soustitre (classic TV), surligneur (highlighter), remplissage (word fill), construction (words appear one by one), impact (big bold), empile (stacked), unmot (one word at a time), bd (comic), editorial (magazine)net
source_idNoInstead of video_url: an upload_id returned by create_upload_link, or the job_id of a finished Klipa job to chain on its result. Empty when video_url is set.
video_urlNoPublic link to a video the user owns or is allowed to edit. Direct file links are not supported (files go through create_upload_link). Empty when source_id is set.
words_per_lineNoMaximum words shown at once (1-8); 0 = style default
second_languageNoOptional ISO code (e.g. 'en', 'es') to add a translated line under the original
translation_onlyNoShow only the translation (requires second_language)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare the mutation profile (readOnly=false, destructive=false, idempotent=false, openWorld=true), and the description usefully adds that credits are consumed exactly as on the website. However it is silent on the two things an agent most needs for a non-idempotent, credit-spending job: that it is asynchronous and what identifier is returned for polling and for chaining via source_id.

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?

Four short sentences, front-loaded with the core action, then progressively adding translation, credit cost, and style discovery. No filler beyond mild promotional wording ("stylish"); every sentence carries a distinct piece of information.

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

Completeness3/5

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

For a credit-spending, non-idempotent media job with six parameters and no output schema, the description omits the return contract (job_id / result URL) and expected processing behavior, so an agent cannot tell how to follow up. The schema compensates on inputs, but the output side is unrecoverable from structured data.

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

Parameters3/5

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

Schema description coverage is 100% and every parameter, including the style enum and the source_id/video_url mutual exclusivity, is documented in the schema itself. The description adds only the count of styles (11) and the existence of a translated second line, both already implicit in the schema, so the baseline 3 is appropriate.

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

Purpose4/5

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

States a specific compound action: transcribes speech AND burns animated subtitles into the video, with a concrete visual (word-by-word highlight like TikTok/Reels) and the option of a second translated line. This clearly separates it from plain transcription tools, though it never explicitly names transcribe_video as the transcript-only alternative.

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 clear routing context: style selection is handled by pointing to show_subtitle_styles ("11 styles, shown as pictures by show_subtitle_styles") and notes that the call spends the user's Klipa credits. It lacks an explicit when-not-to-use statement (e.g., use transcribe_video if you only want text), which keeps it off a 5.

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