Skip to main content
Glama

add_scene

Adds a named scene with one shot, after a chosen scene or at the end, and shows it. Use it to start a new place or moment in an animated video.

Instructions

Add a scene (a group of shots, usually a new place or moment) with one shot in it, and show it. The shot starts like the app's + Scene: the last shot's place, light and cast (or the style's plain place), a still medium camera, 3 seconds. Returns the new scene id, shot id and cast ids. One undo step for the person. To add a shot to an existing scene, use add_shot.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "add_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoLike 'The chase'. Left out: Scene N.
afterNoScene id or index to put it after. Left out: after the last scene.
emptyNotrue: start with nobody in the shot.
lightNoLighting preset id (library lights).
placeNoPlace preset id. Ids must come from the current style: call library to see them (a wrong id is refused with the valid list).
cameraNoCamera move id (library cameras).
secondsNoLength of its first shot in seconds (3 if left out).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.2
    • changedInput schema / properties / camera / description
      Previous value: -"Camera move id."New value: +"Camera move id (library cameras)."
    • changedInput schema / properties / light / description
      Previous value: -"Lighting preset id."New value: +"Lighting preset id (library lights)."
    • addedInput schema / properties / seconds / description
      Added value: +"Length of its first shot in seconds (3 if left out)."
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false), it discloses that the new scene's first shot inherits the last shot's place/light/cast or falls back to the style's plain place, that the response carries scene/shot/cast ids, and that it costs one undo step. Return format and undo semantics are exactly the sort of context annotations cannot supply; only error/refusal behavior is left to the schema.

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 and its defaults, then the return value, then the sibling redirect. "The shot starts like the app's + Scene" is a UI reference that costs a little scanning but earns its place by anchoring the defaults.

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 7-optional-param creation tool with no output schema, the definition covers defaults, return ids, undo behavior, and the sibling alternative. Id-validity and refusal behavior live in the schema (place description names the library call and the refusal-with-valid-list behavior), so there is no meaningful gap left for the description to fill.

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 coverage is 100%, so baseline is 3, but the description adds real meaning the schema lacks: omitted place/light/cast fall back to the previous shot's values rather than to nothing, and 'seconds' defaults to 3. That clarifies the semantics of leaving six of seven optional params unset.

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 specific verb and resource ("Add a scene"), defines what a scene is ("a group of shots, usually a new place or moment"), and notes the side effect of creating one shot and showing it. It also explicitly distinguishes itself from the sibling add_shot.

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 routes the agent away from this tool with the explicit instruction "To add a shot to an existing scene, use add_shot," and the default-inheritance sentence clarifies the intended context of a fresh scene. It stops short of covering other overlapping paths such as duplicating an existing scene, so it is clear context rather than a full when/when-not matrix.

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