Kuro

Add a sound to a film

add_storyboard_sound

Place ready audio the account already holds — a voice-over, music or an audio upload — on a film as a sound card. from_scene is the first scene it covers (absent is the start); offsets, the source window, length (loop, once, in_full) and gain_db are optional, and a card that names neither length nor gain lands as a hand-drop would. Sounds are listed in the answer's sounds array, numbered from 1. One undo step; undo_storyboard takes it back. Spends no credits.

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": {
      "storyboard_id": "<storyboard_id>",
      "reference": "<reference>"
    },
    "name": "add_storyboard_sound"
  }
}

Input Schema

Name	Required	Description
`length`	No
`gain_db`	No
`reference`	Yes
`from_scene`	No	First scene the card covers. Absent means from the start.
`storyboard_id`	Yes
`source_in_seconds`	No
`source_out_seconds`	No
`start_offset_seconds`	No
`loop_duration_seconds`	No

Output Schema

Name	Required	Description	Default
`cast`	Yes
`brief`	Yes
`notes`	Yes
`quote`	No
`texts`	Yes
`scenes`	Yes
`sounds`	Yes
`videos`	Yes
`credits`	Yes
`history`	Yes
`message`	Yes
`skipped`	No
`started`	No
`stopped`	No
`accepted`	No
`receipts`	No
`schedule`	Yes
`settings`	Yes
`reference`	No
`storyboard`	Yes
`download_url`	No
`generation_id`	No
`remaining_scenes`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 26, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the annotations: one undo step with the specific reversing tool, zero credit spend, the default card behavior when neither length nor gain is supplied, and the position of the created card in the response's sounds array. The annotations only give the generic non-readonly/non-destructive/non-idempotent profile, so this adds real decision-relevant context.

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?

One dense paragraph, front-loaded with what the tool does before the parameter and side-effect details. The telegraphic fragments ('offsets, the source window, length (loop, once, in_full)') are efficient but occasionally terse enough to require re-reading.

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?

Output schema exists, yet the description usefully notes the sounds array numbering; cost, undo behavior and defaults are all covered. The missing explanation of the required `reference` object is the one thing an agent genuinely needs before calling.

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?

With schema description coverage at 11% the description must carry the load, and it does explain from_scene, the source-window offsets, the length enum and gain_db as optional. However it never mentions the required `reference` parameter or its upload/generation discriminant shape, and loop_duration_seconds is unaddressed, leaving two significant gaps.

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?

Specific verb and resource: places audio the account already holds onto a film as a sound card, and enumerates the accepted audio kinds (voice-over, music, upload). The phrase 'ready audio the account already holds' clearly separates it from generate_music/generate_voiceover siblings.

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?

The 'already holds' framing tells the agent this is for existing audio rather than generation, and undo_storyboard is named as the reversal path. It stops short of explicitly naming generate_music/cast_voice as the alternative for audio that does not yet exist.

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

All Kuro 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?