ChatCut

manage_custom_voice

List the current user's cloned voices, preflight creation access, create a Fish Audio voice clone from an uploaded project audio asset, apply one to the current request after its Pro entitlement check, rename or delete it, or regenerate a short preview. Load the voice Skill before use. Clone only after the user has uploaded a supported audio file and explicitly confirmed that the voice is theirs or they have permission to clone it. The backend enforces the free-trial/Pro slot policy and preview text length. Preview returns a URL for a voice audition card. Apply requires Pro but does not generate audio or consume credits. Use submit_voice with provider fish-audio and the returned customVoiceId to generate final audio.

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": "manage_custom_voice"
  }
}

Input Schema

Name	Required	Description
`name`	No	Required for clone and rename.
`action`	Yes
`projectId`	No	Project for this call (full ID or unambiguous prefix). Explicit-timeline calls never change the target of later calls; legacy project selection applies otherwise.
`timelineId`	No
`previewText`	No	Required for clone/preview. Contextual sample copy limited to 100 Unicode characters.
`languageCode`	No	For clone: reference audio's spoken language code, e.g. en, zh, or es. Supply it when known; otherwise the backend uses the asset's transcript language. This is not the UI locale or preview text language.
`customVoiceId`	No	Required for apply, preview, rename, and delete. Accepts a unique id prefix.
`sourceAssetId`	No	Required for clone. A project-local ChatCut audio asset ID; an unambiguous ID prefix returned by browse_assets is accepted. Video assets and detached timeline audio are not valid clone sources.
`confirmedDelete`	No	Required and true for delete, after the user explicitly confirmed permanent deletion.
`confirmedConsent`	No	Required and true for clone. The user explicitly confirmed ownership or permission.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedNov 5, 2026

TDQS

A3.7/5.0

Behavior2/5

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

The description discloses a lot the annotations do not: backend enforcement of the free-trial/Pro slot policy and preview text length, that apply requires Pro but does not generate audio or consume credits, and that preview returns a URL. However, it also describes an action that performs a permanent deletion ('delete', requiring confirmedDelete after explicit confirmation of permanent deletion), which conflicts with destructiveHint=false in 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The action inventory is front-loaded in a single dense sentence, followed by short constraint sentences, which is efficient for a seven-action tool. It is long, but nearly every clause carries a rule or a routing hint rather than 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?

With ten parameters, no output schema, and a destructive action in the mix, the description covers preconditions, entitlement behavior, consent requirements, and the return value of preview. Only the return shape for list/check-create-access and the failure modes of clone are left implicit, which is minor.

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 coverage is 80%, so parameter meaning is largely already documented (required-for-X notes on name, previewText, customVoiceId, sourceAssetId, confirmedConsent, confirmedDelete). The description adds mostly cross-parameter behavior (backend slot policy, preview length enforcement) rather than new per-parameter semantics, so the baseline of 3 applies.

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?

The first sentence enumerates every supported action with a concrete verb and resource (list cloned voices, check creation access, clone from an uploaded asset, apply to the current request, rename/delete, regenerate a preview), so an agent knows the full action surface without opening the schema. It also names a sibling (submit_voice) and its role, distinguishing cloning from final audio generation.

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 explicit preconditions (load the voice Skill first; clone only after the user uploaded a supported audio asset and explicitly confirmed ownership/permission) and routes final audio generation to submit_voice with provider fish-audio. It does not, however, say when to choose this over other adjacent siblings such as manage_voice or isolate_voice.

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

All ChatCut 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.