Skip to main content
Glama

Plan an Approved Video Script

video_storyboard_create
DestructiveIdempotent

Create a vertical video storyboard for the user-approved script in an existing project. Spends planning credits; returns scene narration, factual review notes, references and the production credit estimate. Does not generate images or animate video. Existing account access applies.

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": {
      "projectId": "<projectId>",
      "script": "<script>",
      "workspaceId": "<workspaceId>",
      "idempotencyKey": "<idempotencyKey>",
      "confirmScriptApproved": "<confirmScriptApproved>"
    },
    "name": "video_storyboard_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
genreNoGenre pack id. GET /generation-options/faceless lists them in genres, with what each format needs in formats.
scriptYes
voice_idNo
projectIdYesUUID string.
series_idNo
multi_shotNoLet one video generation cover several timed shots and camera angles. Adjacent script blocks are grouped into takes.
storyboardNoGenerate one approved storyboard sheet instead of per-scene keyframes and use it as the video reference. Implies multi_shot.
video_modelNo
workspaceIdYes
clip_secondsNoTarget length of each multi-shot generation. Defaults to 15, or the model maximum when lower.
story_kit_idNo
visual_styleNo
character_idsNo
idempotencyKeyYes
image_model_idNo
caption_style_idNo
include_captionsNo
planner_model_idNo
confirmScriptApprovedYes
generate_sound_effectsNo
target_duration_secondsNo
use_seamless_transitionsNoChain each scene's clip into the next with end frames. Applies only to video models that support end frames.
generate_background_musicNo
style_reference_asset_idsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / genre / description
      Previous value: -"Genre pack id. GET /generation-models?kind=faceless lists them."New value: +"Genre pack id. GET /generation-options/faceless lists them in genres, with what each format needs in formats."
  2. Changed1 schema field changed
    • addedInput schema / properties / use_seamless_transitions
      Added value: +{
      +  "description": "Chain each scene's clip into the next with end frames. Applies only to video models that support end frames.",
      +  "type": "boolean"
      +}
  3. Changed4 schema fields changed
    • addedInput schema / properties / clip_seconds
      Added value: +{
      +  "description": "Target length of each multi-shot generation. Defaults to 15, or the model maximum when lower.",
      +  "maximum": 60,
      +  "minimum": 4,
      +  "type": "integer"
      +}
    • addedInput schema / properties / genre
      Added value: +{
      +  "description": "Genre pack id. GET /generation-models?kind=faceless lists them.",
      +  "maxLength": 100,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / multi_shot
      Added value: +{
      +  "description": "Let one video generation cover several timed shots and camera angles. Adjacent script blocks are grouped into takes.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / storyboard
      Added value: +{
      +  "description": "Generate one approved storyboard sheet instead of per-scene keyframes and use it as the video reference. Implies multi_shot.",
      +  "type": "boolean"
      +}
  4. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare non-read-only, destructive, idempotent and open-world, but the description adds genuinely new behavior: it consumes planning credits, and it names the returned artifacts (scene narration, factual review notes, references, production credit estimate). It does not address what is destroyed or overwritten when run against a project that already has storyboard data, or how idempotencyKey affects replays — gaps that matter given destructiveHint=true.

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?

Four tight sentences, front-loaded with the action, then cost, then returns, then boundaries — no filler. The closing 'Existing account access applies' is the weakest line, vague enough that it could be dropped or made specific.

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

Completeness3/5

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

For a destructive, credit-spending 24-parameter tool this covers the essentials (cost, outputs, exclusions, prerequisite) and need not explain return values because an output schema exists. It stops short of describing the workflow relationship with video_storyboard_approve/revise/get or what happens to a pre-existing storyboard, which for a tool this complex leaves real gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25% across 24 parameters, so the description carries the burden — and it barely does. It implies the required script and confirmScriptApproved via 'user-approved script', but says nothing about genre, story_kit_id, multi_shot, storyboard, clip_seconds, visual_style, character_ids, or the model-id fields, all of which materially change the output.

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+resource+shape: 'Create a vertical video storyboard for the user-approved script in an existing project.' It also explicitly excludes adjacent capabilities ('Does not generate images or animate video'), so an agent can tell it apart from generation_video_create and the storyboard_approve/revise siblings without reading schemas.

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?

Prerequisites are clear: the script must already be user-approved, the project must exist, and account access is required. The negative scoping ('does not generate images or animate video') implicitly routes image/video work elsewhere, but no sibling is named explicitly (e.g., revise vs approve vs get), so the agent still has to infer the workflow ordering.

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.

Resources