Skip to main content
Glama

Score a video

score_video

Compose music to a video and, by default, return the video with the music under it.

    Tuney finds the picture cuts, speech and sonic logo, then arranges a track to them: the music
    ends where the logo starts (or at the end), the turning point lands on the strongest cut in
    the middle, hits land on other strong cuts outside speech, and the music is lowered while
    people speak in the rendered video.

    - prompt: describe the music ("upbeat pop for a sneaker ad"); or cue_id: one of the user's tracks.
    - ending: "fade" lands exactly on the length; "short" ends on a stab.
    - turning_point_seconds / no_turning_point: override the automatic turning point.
    - music_end_seconds / logo_start_seconds: where the music must stop (a sonic logo starts).
    - hits: sound effects on strong cuts; render: also return the scored video.

    Scoring takes about a minute; if the result says timed_out, call wait_for_task with the
    task_id and kind="score_video". The result has the track (preview_url), the plan, and the
    video link when rendered. Previews and renders are free; downloading the track costs 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": {
      "video_id": "<video_id>"
    },
    "name": "score_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
hitsNo
cue_idNo
endingNofade
promptNo
renderNo
video_idYes
no_turning_pointNo
music_end_secondsNo
logo_start_secondsNo
turning_point_secondsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses runtime (~a minute), async/timeout semantics with the exact recovery call, the cost model (previews and renders free, downloading the track costs credits), and the audible behavior (music ducked under speech, music ending at the logo). That is substantial context the annotations cannot convey.

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?

It is front-loaded with the core action, then uses a scannable bullet list for parameters and a closing paragraph for timing/cost. Every bullet maps to real parameters, though the mechanism paragraph (cuts, speech, sonic logo) is somewhat verbose relative to what an agent needs to invoke the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, long-running, credit-consuming tool, the description covers timing, async recovery, cost, and output contents; an output schema exists, so return-value details need not be spelled out further. Nothing an agent needs to call this correctly appears to be missing.

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 description coverage is 0%, so the description must carry parameter meaning, and it largely does: it explains prompt, cue_id, ending (with the semantic difference between 'fade' landing exactly on length and 'short' ending on a stab), turning_point_seconds/no_turning_point, music_end_seconds/logo_start_seconds, hits, and render. Only video_id is left unelaborated, and the default values are not restated.

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 opening sentence gives a specific verb+resource ('Compose music to a video') and immediately disambiguates the ambiguous name 'score' by describing the default output (video with music under it). The follow-up paragraph explains the underlying mechanism (cut detection, speech ducking, logo alignment), which lets an agent distinguish this from siblings like generate_track or render_video.

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?

It gives concrete usage conditions: use prompt for described music vs cue_id for an existing track, and explicitly routes the agent to wait_for_task with kind="score_video" when the result is timed_out. It also flags the preview-vs-download cost distinction. What it lacks is an explicit statement of when NOT to use this tool (e.g. when the goal is only to render an existing track).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.