Skip to main content
Glama

Revise one scene of a draft

revise_scene
DestructiveIdempotent

Change ONE scene of a draft in place: its narration (scriptText), its visualPrompt and/or its durationSeconds. Scene numbers start at 1 (see get_draft). Only the fields you pass change. Screened like any prompt. Free; draft only. Requires the "video:create" scope.

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": {
      "draftId": "<draftId>",
      "scene": "<scene>"
    },
    "name": "revise_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
sceneYesScene number, starting at 1.
draftIdYes
scriptTextNoThe narration of this scene, exactly as it will be spoken.
visualPromptNoWhat the image should show. Leave empty to let StoryShort write it at render.
durationSecondsNoScene length (default 10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations it discloses cost ('Free'), auth scope, content moderation ('Screened like any prompt'), and the crucial partial-mutation semantic ('Only the fields you pass change'), which explains how this destructive overwrite actually behaves. That is real added value on top of destructiveHint/idempotentHint rather than a restatement of them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Every clause is front-loaded and load-bearing: the action, the editable fields, the numbering rule, the partial-update rule, moderation, cost, and scope all come in a few dense sentences with no 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?

For a mutation tool with no output schema, it covers scope, cost, moderation, and mutation semantics well. The remaining gap is what happens after the edit (whether the scene must be re-rendered and what the call returns), which an agent would still have to discover.

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 field meanings are already documented; the description's scene-numbering note largely echoes the schema's own 'Scene number, starting at 1.' The one genuine addition is the partial-update rule, which clarifies that optional fields are truly optional, though no format or interaction details for scriptText vs visualPrompt are added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Change ONE scene of a draft in place') and enumerates exactly which fields are editable (scriptText, visualPrompt, durationSeconds). It is immediately clear this edits a single scene rather than the whole draft, but it never names the nearby sibling update_draft, so the boundary between revising a scene and updating a draft is left to inference.

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 establishes prerequisites ('Requires the "video:create" scope'), scope ('draft only'), and points to get_draft for valid scene numbers, which is exactly the context needed before calling. It stops short of stating when not to use it or explicitly naming an alternative for whole-draft edits.

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