Skip to main content
Glama

cast

Add, change, or remove characters and objects in a shot, then set their position, pose, size, facing, color, or accessory and get shot and member IDs.

Instructions

Add, change or remove a character or object in a shot. op add needs ref (a character or object id of the style); change and remove need member (its id from get_shot, or its name). Ids must come from the current style: call library to see them (a wrong id is refused with the valid list). A character added without x is spaced out automatically. Returns the shot and member ids. One undo step for the person. To make the cast move or feel something, use act; for animation over time, use keys.

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": "cast"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoLeft (-) to right (+); about -8 to 8 is in frame.
yNoHeight above the ground; 0 stands on it.
zNoNear (+) to far (-); 0 is the front line.
opNoadd if left out.
refNoCharacter or object id (add), or a new one of the same kind (change swaps it).
nameNoA name for this member, like 'Mia'. Used by act and in undo notes.
poseNoA pose id the character offers.
shotNoThe shot's id (from get_project). Left out: the shot on screen.
sizeNo1 is normal size.
spinNoDegrees, turning in the picture like a wheel.
tintNoColour "#RRGGBB", or "" to remove.
turnNoDegrees, turning round like on a stage.
auto_xNochange: true lets the scene space it out again.
facingNoWhich way it looks.
memberNoMember id or name (change, remove).
accessoryNohat, crown, party, bow (only characters that can dress), or "".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.1.2
    • addedInput schema / properties / facing / description
      Added value: +"Which way it looks."
    • addedInput schema / properties / name / description
      Added value: +"A name for this member, like 'Mia'. Used by act and in undo notes."
    • addedInput schema / properties / size / description
      Added value: +"1 is normal size."
    • addedInput schema / properties / x / description
      Added value: +"Left (-) to right (+); about -8 to 8 is in frame."
    • addedInput schema / properties / y / description
      Added value: +"Height above the ground; 0 stands on it."
    • addedInput schema / properties / z / description
      Added value: +"Near (+) to far (-); 0 is the front line."
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations cover only the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds real behavioral context: 'one undo step for the person', an incorrect id being 'refused with the valid list', automatic spacing when x is omitted, and the returned ids. The 'remove' behavior with destructiveHint=false is consistent with the stated single undo step, so there is no contradiction, though it could be stated more plainly.

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?

The operation contract is front-loaded in the first two sentences and nearly every sentence carries a distinct rule. A few statements are dense and compressed (the op/ref/member shorthand) and would read better split, but none of the content is filler.

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 16-parameter, 0-required, no-output-schema mutation tool, the description covers operand requirements per operation, id provenance and error behavior, spacing defaults, return values, undo granularity, and routing to act/keys. That is everything an agent needs to invoke it correctly.

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 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema cannot: which of ref/member is required per op value and that a 'change swaps' the reference for a new one of the same kind. It doesn't explain placement-range or accessory enum values, but the schema already does that well.

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 first sentence names specific verbs and resource: 'Add, change or remove a character or object in a shot', and the closing sentence explicitly separates it from act (performance) and keys (animation over time). An agent can distinguish this from get_shot, library, and move without opening any schema.

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 conditional requirements per operation ('op add needs ref', 'change and remove need member'), the prerequisite that ids must come from the current style with a pointer to library, and two named alternatives (act, keys) with the conditions that select them. When-not guidance is implicit in the id-validation rule, which is a close substitute.

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