Skip to main content
Glama
Claude ATEM MCP
by La8Grt8

Set Super Source Layout

atem_set_supersource_layout
Idempotent

Configures all four Super Source boxes at once using layout presets or custom box settings, letting ATEM operators arrange inputs for side-by-side, PiP, grid, or three-up scenes.

Instructions

Set up a Super Source layout using a preset or custom box configuration. Configures all 4 boxes at once.

Presets arrange boxes with sensible defaults — just provide the input sources.

Args:

  • preset (string, optional): Layout preset name:

    • "side_by_side": Two equal boxes side by side (sources: [left, right])

    • "pip_bottom_right": Full-screen with small PiP bottom-right (sources: [background, pip])

    • "pip_bottom_left": Full-screen with small PiP bottom-left (sources: [background, pip])

    • "pip_top_right": Full-screen with small PiP top-right (sources: [background, pip])

    • "pip_top_left": Full-screen with small PiP top-left (sources: [background, pip])

    • "grid_2x2": Four equal boxes in 2x2 grid (sources: [topLeft, topRight, bottomLeft, bottomRight])

    • "three_up": Large left + two stacked right (sources: [large, topRight, bottomRight])

  • sources (array of numbers, optional): Input source numbers for each box position in the preset

  • boxes (array of objects, optional): Custom box configs (overrides preset). Each: { enabled, source, x, y, size, cropped, cropTop, cropBottom, cropLeft, cropRight }

  • ssrcId (number, optional): Super Source index (default: 0)

Examples:

  • Side-by-side cameras 1 & 2: preset="side_by_side", sources=[1, 2]

  • 2x2 grid all cameras: preset="grid_2x2", sources=[1, 2, 3, 4]

  • PiP camera 3 over camera 1: preset="pip_bottom_right", sources=[1, 3]

Input Schema

NameRequiredDescriptionDefault
boxesNoCustom box configurations (array of up to 4 box objects, overrides preset)
presetNoLayout preset name
ssrcIdNoSuper Source index (default: 0)
sourcesNoInput source numbers for each box position in the preset

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.5.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare idempotent, non-destructive, non-open-world writes. The description adds meaningful context beyond them: it acts on all four boxes atomically and custom boxes override the preset. It does not say whether unspecified boxes are reset or disabled, which would have completed the picture.

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?

Front-loaded with the purpose, then preset definitions, then concrete examples — all useful. The preset bullet list is long but each entry carries ordering semantics not present in the enum, so it earns its space; examples partly overlap with the bullets.

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 4-param, no-output-schema tool with full annotation coverage, the description covers operation, presets, precedence and examples. Remaining gap: no statement about what happens to boxes left unspecified or whether the existing layout is replaced.

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

Parameters5/5

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

Schema coverage is 100%, yet the description still adds information the schema cannot: the source ordering per preset (e.g. [background, pip] for PiP modes, [topLeft, topRight, bottomLeft, bottomRight] for grid) and the override precedence. This is exactly the value-add parameter semantics should provide.

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 ('Set up a Super Source layout') plus the key differentiator: it configures all 4 boxes at once, distinguishing it from the sibling atem_set_supersource_box which handles one box. An agent can select between the two without opening either schema.

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?

Explains the preset-vs-custom choice and that 'boxes' overrides 'preset', which is real routing guidance. It does not name the sibling tools (set_supersource_box/art/border, get_supersource_state) as alternatives or exclusions, so it falls short of a 5.

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