DubSync

Start an authorized translation

dub_create_project

Idempotent

Sends the uploaded video and audio for AI processing and starts translation, consuming existing credits or free allowance. First explain this processing and obtain affirmative user approval for the exact source, target language and full/free-preview scope, including content and speaker/voice rights. Do not treat OAuth consent as processing approval. Reuse the exact idempotency key and input after a timeout.

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": {
      "sourceAssetId": "<sourceAssetId>",
      "targetLanguage": "<targetLanguage>",
      "consentAccepted": "<consentAccepted>",
      "userConfirmed": "<userConfirmed>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "dub_create_project"
  }
}

Input Schema

Name	Required	Description
`title`	No
`freePreview`	No
`sourceAssetId`	Yes	The assetId of media uploaded and completed through the DubSync upload API.
`userConfirmed`	Yes	True only after affirmative user authorization for this exact translation and its allowance/credit use.
`idempotencyKey`	Yes	A stable unique key for this operation. Reuse it with the exact same input after a timeout; never generate a new key to retry.
`targetLanguage`	Yes	A language code returned by dub_list_languages.
`consentAccepted`	Yes	True only after the user agrees to send this video/audio for AI processing and confirms necessary content and speaker/voice rights for this request.

Output Schema

Name	Required	Description	Default
`data`	Yes	The safe public API response, or resumable-upload status.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 10, 2026

removedInput schema / properties / subtitleLanguage

Removed value: -{
-  "anyOf": [
-    {
-      "maxLength": 20,
-      "minLength": 2,
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "description": "Optional subtitle language supported by DubSync."
-}

First observedNov 10, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only flag write/idempotent/non-destructive/open-world; the description adds the material facts an agent needs: credits or free allowance are consumed, the media leaves the system for AI processing, human consent plus rights confirmation is mandatory, and timeouts must be retried with the same key. That is real added context rather than a restatement of the annotation flags.

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 tight sentences, front-loaded with what happens and what it costs, then the consent gate, then the retry rule. No filler; each sentence changes agent behavior.

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 so return values need no explanation, and the consent/cost/idempotency burden is fully covered for a billable mutation. The only gap is failure behavior, e.g. what happens when neither credit nor free allowance remains, and no pointer to checking balance first.

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 71% and the schema already documents sourceAssetId, userConfirmed, idempotencyKey, targetLanguage and consentAccepted precisely. The description still adds meaning by framing the approval scope as 'source, target language and full/free-preview scope', which clarifies the otherwise undocumented freePreview toggle, though title and the pattern constraints are left to the schema.

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 concrete verb and outcome: sends already-uploaded media for AI processing and starts a translation, with the cost consequence spelled out. The phrase 'the uploaded video and audio' implicitly positions it after dub_create_upload/dub_complete_upload, so an agent can distinguish it from the upload-side tools without opening a 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?

Gives explicit preconditions (explain the processing, obtain affirmative approval for the exact source, target language and full/free-preview scope) and an explicit exclusion (OAuth consent is not processing approval). It also names the retry behavior: reuse the exact idempotency key and input after a timeout rather than generating a new one.

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

All DubSync tools Inspect

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

Need Help?