agent-video-engine

Overview Schema Source Related Servers Discussions Admin

transcribe

Generate cached local word-level captions from video audio with whisper.cpp, returning a durable job ID and applying results only when the project revision is unchanged.

Instructions

Start cached, local word transcription with whisper.cpp. Returns a durable job ID. Never uploads footage or downloads models. Applies results only if the project revision is unchanged.

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": {
      "projectDir": "<projectDir>",
      "expectedRevision": "<expectedRevision>",
      "assetId": "<assetId>"
    },
    "name": "transcribe"
  }
}

Input Schema

Name	Required	Description	Default
`assetId`	Yes
`language`	No		en
`modelPath`	No
`projectDir`	Yes	Absolute path of the local video project directory
`expectedRevision`	Yes	Revision returned by project_inspect. Prevents overwriting newer edits.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.0.0Nov 6, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and the description genuinely adds beyond them: local-only processing, no uploads or model downloads, async job semantics, and an optimistic-concurrency guard ("Applies results only if the project revision is unchanged"). It still doesn't say whether an existing transcript is overwritten or how a stale-revision result is reported.

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?

Four short sentences, front-loaded with the action and the return contract, then the privacy and consistency constraints. Every sentence carries distinct information with no filler.

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?

For a mutation tool with no output schema, it covers the key facts: local/cached execution, job-ID return, and the revision precondition. What is missing is how long a cached transcription takes, how to poll or retrieve the result, and what happens to a stale-revision run.

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

Parameters2/5

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

Schema coverage is only 40%: projectDir and expectedRevision are documented in the schema, but assetId, language, and modelPath have no explanation anywhere. The description gestures at the revision check but adds nothing about which asset is transcribed, what modelPath means, or the language default, so it fails to compensate for the coverage gap.

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?

"Start ... word transcription with whisper.cpp" gives a specific verb and resource, and the snippet "Returns a durable job ID" clarifies it is an async job starter rather than a synchronous result. It does not name a sibling (e.g., transcript_import) to differentiate itself explicitly, so it stops short of a 5.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: returning a job ID suggests following up via job_get/job_list, and the revision guard hints at a required project_inspect call first. However, it never says when to choose this over transcript_import or transcript_search, and no exclusions are given.

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