Skip to main content
Glama
Sign In

ChatCut

by io.chatcut
OverviewDiscussionsAdmin

video_translation

Load the video-translation Skill for ALL such requests, with or without lip-sync; it selects the route and owns review. Use this tool only for integrated provider translation, never merely to transcribe or review independent dubbing. Use list_languages, prepare, get, generate on the same taskId. Preparation and edits do not charge; supplier draft cost unverified. prepare never renders; get is read-only. Both lip-sync choices require review. Show editable source-language text by default; target review is optional. Users need not know the target language. Apply source corrections to the target draft and save both SRTs on the same revision. Show connected readable text; keep cue timing internally. The provider does not retranslate source corrections; never render an unsaved preview. generate requires the exact authorized revision and an explicit audioOnly: true dubs speech and keeps the picture; false also lip-syncs mouths, so do not call submit_lipsync afterward. The whole asset is processed; export ranges first. No speaker/spatial selector; time crops cannot isolate overlapping voices or protect others. Edit final target wording in the existing draft. Complete rewrites default to voice/TTS with reviewed audio and timing, then optional submit_lipsync; new presenter performances use digital-human. Voice samples are not final dialogue. Subtitle-only work is separate. On timeout get the same task before retrying. Fix content in drafts, voice in audio, mouths in lip-sync. Never repeat paid stages to fix import. Report unsupported capabilities; don't silently change treatment. At most 10 video generations run at once per account across video tools; extra submits are rejected, so wait for a running job to finish instead of retrying.

External MCP spend rule: list_languages/get are read-only. prepare may incur translation preprocessing charges; generate renders the reviewed revision. User authorization must cover the exact action and scope. Never silently create variants or bypass draft review.

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": {
      "action": "<action>"
    },
    "name": "video_translation"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional output asset name.
actionYeslist_languages is a free catalog read. prepare creates or edits the same translation task without charging the user. get reads its actual draft/status without generating. generate is the billable render of only the approved revision.
taskIdNoRequired for get/generate and editing an existing draft. Reuse this ID to recover after interruption.
revisionNogenerate: exact displayed and authorized draft revision. It cannot be replaced with newly supplied text.
audioOnlyNogenerate, required: true dubs speech only; false also lip-syncs mouths. The video-translation Skill chooses; both require content review. For speech-only edits, replace selected non-overlapping speech intervals and retain other turns' audio; time selection cannot separate overlapping mixed voices.
projectIdNoFull project UUID. Required for external browser work; internal agents may omit. Execution/explicit-timeline calls never change later calls' target.
timelineIdNoFull timeline UUID, not a prefix. Required for browser work, even unplaced assets. Get it from read_project or manage_timelines action="list". Never switches visible timeline.
keepDurationNoInitial prepare, default false: allow provider duration adjustment. true disables video stretching to preserve source timing. Neither choice guarantees natural pacing or frame-exact output; inspect actual duration.
sourceAssetIdNoInitial prepare only: whole project video asset. Export a selected section as its own asset first.
idempotencyKeyNoStable key for this browser execution. Reuse only with identical scope and parameters after a lost acknowledgement; applies only to this call.
targetLanguageNoInitial prepare: exact canonical language from list_languages.
browserProfileIdNoOptional browser profile override. Omit to select automatically; do not ask the user to choose.
expectedRevisionNoprepare edit: revision returned by get. Stale edits are rejected; fetch and reconcile instead of overwriting.
sourceTranscriptSrtNoInitial prepare: local SOURCE-language SRT for comparison, retaining actual cue timing. This is not sent as a provider source correction. Omit to use the complete library transcript. On same-task editing, pair source corrections with updated targetTranscriptSrt. This is a ChatCut review reference, not a provider retranslation input; major new dialogue belongs in the new-script workflow.
targetTranscriptSrtNoprepare edit only: revised TARGET-language SRT from get, preserving cue structure. Show readable source/target text to the user, not SRT syntax.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, idempotentHint=false; the description adds the operational surface those flags cannot: prepare/edit are free while generate bills the approved revision, prepare never renders, get is read-only, generate needs the exact authorized revision, at most 10 concurrent video generations per account with extra submits rejected, and retry-by-get on timeout. Nothing here contradicts the annotations.

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 is front-loaded, but the body is a dense run-on of clipped imperative fragments ('Fix content in drafts, voice in audio, mouths in lip-sync.') with the review requirement restated several times. Most sentences carry real operational content, yet the lack of grouping and the telegraphic phrasing make it harder to parse than its length warrants.

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 15-parameter, four-action, non-idempotent tool with no output schema, the description covers billing, review gates, concurrency, recovery and error routing, which is close to complete. Residual gaps are minor: what get actually returns and how status/draft payloads look, though the absence of an output schema keeps that burden low.

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; the description still adds meaning the schema does not, notably that both audioOnly choices require review and that you must not call submit_lipsync after audioOnly=false, plus the rule that users need not know the target language. It does not, however, explain revision/expectedRevision interplay beyond what the parameter descriptions already state.

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 opening sentence establishes the resource (video translation, with or without lip-sync) and the routing model (it selects the route and owns review), and later sentences carve out what it is not: transcription, independent dubbing review, subtitle-only work. The phrase 'ALL such requests' is slightly circular on first read, but the body immediately disambiguates. An agent can distinguish it from submit_lipsync and the digital-human flow without opening the schema.

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

Usage Guidelines5/5

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

Explicit when-to-use ('integrated provider translation'), when-not ('never merely to transcribe or review independent dubbing', 'Subtitle-only work is separate'), and named alternatives (submit_lipsync optional afterward, digital-human for new presenter performances). It also prescribes the action sequence (list_languages, prepare, get, generate on the same taskId) and the recovery path on timeout.

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

All ChatCut toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources