Skip to main content
Glama

captions

Generate word-timed subtitles from narration audio for demo videos; returns a job ID immediately for polling and rejects concurrent runs.

Instructions

Transcribe narration.mp3 to captions with word timing. Returns a jobId immediately — poll job_status. Rejects if another job is running.

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": {
      "dir": "<dir>"
    },
    "name": "captions"
  }
}

Input Schema

NameRequiredDescriptionDefault
dirYesdemo project directory — pass an absolute path
langNorender a language variant from scene.narrations[<code>] over the shared take (artifacts namespaced: audio/<code>/, captions.<code>.*, output/final-demo.<code>.mp4). Omit for the default single-language render.
paramsNostoryboard template params (name → value); each must be declared in the storyboard's params block. Substitutes {{name}} across all stages.
offlineNoapproximate captions from the script — no network/STT
alignScriptNouse script spelling and punctuation with STT word timing

Output Schema

NameRequiredDescriptionDefault
kindYes
jobIdYes
statusYes
demoDirYesresolved absolute demo directory
logFileYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.20.2
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / properties / params / propertyNames
      Added value: +{
      +  "type": "string"
      +}
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed1 schema field changedv0.15.2
    • addedInput schema / properties / alignScript
      Added value: +{
      +  "description": "use script spelling and punctuation with STT word timing",
      +  "type": "boolean"
      +}
  3. First observedv0.9.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and it does disclose the async contract and a single-concurrency rejection rule. It says nothing about permissions, how long the job runs, whether it writes files into the project directory, or whether a rejection is retryable — gaps a caller must discover by trial.

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?

Three short sentences with zero waste: purpose first, then the async return, then the failure condition. Every clause carries actionable information.

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

Completeness4/5

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

An output schema exists and parameter coverage is full, so the description need not explain return values or flags. It covers the async/concurrency contract well; the only meaningful omission is that it does not say which files it produces in the project directory for a mutating job.

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%, so the schema already explains dir, lang, params, offline, and alignScript in detail. The description adds only the implicit input assumption (narration.mp3) and adds nothing about the optional flags, so 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?

The description names a specific verb and resource ('Transcribe narration.mp3 to captions with word timing'), which tells an agent exactly what artifact is produced. It is distinguishable from siblings like render or voice, though it never explicitly contrasts itself with them.

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?

It gives the operational context an agent needs: the call is asynchronous ('Returns a jobId immediately — poll job_status') and fails under concurrency ('Rejects if another job is running'). What is missing is guidance on when to choose this versus render/voice or which sibling handles the same media differently.

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