Skip to main content
Glama

Outil.io

Build video from storyboard

build_video_from_storyboard
Destructive

Fabriquer une vidéo complète (démo produit, site, fonctionnalité, publicité) à partir d’un storyboard, en UN appel : enregistrement réel des sites avec curseur et zooms, images animées, vidéos Pexels, voix off naturelle, sous-titres mot à mot façon CapCut, titres animés, fond dégradé, transitions, musique atténuée sous la voix, puis export MP4. Asynchrone : renvoie id ; suivre get_video_build. Lire get_video_guide (demoVideo) pour écrire un bon storyboard.

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": {
      "name": "<name>",
      "scenes": "<scenes>"
    },
    "name": "build_video_from_storyboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
musicNo
ratioNo9:16
speedNo
voiceNoF2
accentNo#FFD400
exportNo
scenesYes
captionsNo
languageNofr
backgroundNo
resolutionNo1080
transitionNofade

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the description's job is to explain the operation beyond that, and it does: it discloses the asynchronous execution model, that only an id is returned, and that real live websites are recorded (the source of the open-world behavior). It does not mention cost/credit consumption, expected render duration, or what happens on partial failure, which are the remaining gaps for a heavy destructive job.

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 a single dense paragraph, front-loaded with the purpose, then the capability list, then two short operational sentences (async follow-up, guide prerequisite). Every sentence carries information, though the capability list could be trimmed slightly since some items are implied by the schema enums.

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 13-parameter, deeply nested, asynchronous, non-read-only tool with no output schema, the definition supplies the three things an agent needs: what the call produces, that the response is only an id requiring get_video_build polling, and that get_video_guide must be consulted first. Return values need no explanation because the description states the return is just an id.

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 description coverage is 0% across 13 parameters with deep nesting, so the description must compensate; it does add real semantic value by mapping the scene vocabulary to concrete visual modes (website capture with cursor/zoom, animated image, Pexels video, gradient color) and by naming the effect systems (captions, titles, transitions, music ducking, voiceover). However, it never touches the many enum/numeric knobs the schema exposes (ratio, resolution, voice IDs, caption presets, speed, accent, language, scene limits), leaving more than half the parameter surface undocumented anywhere.

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 description opens with a precise verb+resource ("Fabriquer une vidéo complète ... à partir d'un storyboard") and immediately enumerates what the output contains (live site capture with cursor/zoom, animated images, Pexels stock, voiceover, captions, titles, gradient background, transitions, ducked music, MP4 export). It is clearly distinguishable from the granular edit siblings (add_video_text, add_video_clip, etc.) because it explicitly claims a one-call full build.

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?

It states the operating mode ("en UN appel"), the async contract and the follow-up tool ("suivre get_video_build"), and names a prerequisite-reading alternative ("Lire get_video_guide (demoVideo) pour écrire un bon storyboard"). An agent knows both when to pick this and what to do before and after calling it.

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.