Skip to main content
Glama

Create autopilot

create_autopilot

Create a beat-synced autopilot that randomizes a COMP's controls or cycles cues every N beats to keep visuals evolving automatically.

Instructions

Build a beat-driven auto-VJ: a Beat CHOP + a CHOP Execute DAT that, every N beats, either randomizes a target COMP's numeric controls (a hands-free drift, set by Amount) or cycles through its stored cues — so a set keeps evolving on its own. Creates a new baseCOMP under parent_path holding the Beat CHOP and the engine DAT; it modifies the target COMP at comp_path (its custom controls or stored cues) live at runtime. Live Active/Beats/Amount knobs let you pause or retune on stage. Reuses the tempo clock, randomize_controls and manage_cue mechanisms. Pair with a generated system (or a control panel) as the target. Returns a summary plus a JSON block with the container path, created node paths, the target, mode, beats, amount, engine path, any node errors, and warnings (no preview image — the output is a CHOP engine, not a TOP).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo'randomize' nudges the COMP's numeric controls toward new random values each trigger (works on any COMP with controls). 'cue' cycles through the COMP's stored cues (needs cues from manage_cue).randomize
beatsNoFire an action every N beats (4 = once per bar at 4/4).
amountNo(randomize) How far to move toward random each trigger: 1 = full scramble, low = gentle drift.
comp_pathNoCOMP the autopilot drives — its numeric custom controls (randomize mode) or its stored cues (cue mode). Usually a generated system container or a control panel./project1
parent_pathNoWhere to create the autopilot engine./project1
Behavior4/5

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

The description discloses that it creates a new baseCOMP under parent_path, modifies the target COMP live at runtime, and returns a summary plus warnings. It also clarifies the output is a CHOP engine, not a TOP, adding context beyond the annotations. No contradiction with readOnlyHint/destructiveHint.

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 description is multi-sentence but every sentence adds necessary context: purpose, mechanism, runtime controls, reuse, pairing, and return value. It is front-loaded and appropriately sized for a tool of this complexity.

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?

Despite no output schema, the description lists detailed return contents (container path, node paths, target, mode, beats, amount, engine path, errors, warnings) and the caveat about no preview image. It covers practical usage and side effects thoroughly.

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?

Input schema covers all 5 parameters with descriptions (100% coverage). The description adds context about parameter interactions (e.g., Amount scales randomize drift) but does not significantly extend the schema's semantic detail. Baseline of 3 is appropriate given full schema coverage.

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 description uses specific verb 'Build' and clearly states the tool creates a beat-driven auto-VJ with a Beat CHOP and CHOP Execute DAT. It distinguishes from siblings by detailing the two operating modes (randomize vs cue) and explicitly references reusing randomize_controls and manage_cue mechanisms.

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?

The description gives usage context: 'Pair with a generated system (or a control panel) as the target' and explains when each mode is appropriate. It doesn't explicitly state when not to use it, but the reference to reusing randomize_controls and manage_cue implies this is an orchestration layer rather than those direct tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lucasmaher-hash/touch-designer-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server