Skip to main content
Glama

Create transition (A→B)

create_transition

Build a parameterized A→B transition with a Progress knob and five styles like dissolve or luma_wipe. Outputs a Null for post-processing with exposed controls.

Instructions

Build a parameterized A→B transition over a single 0–1 Progress knob — the executable core of VJ cutting. Creates a new baseCOMP under parent_path holding two sources (brought in via Select TOPs, or built-in contrasting test looks when omitted) and one of five transition styles: 'dissolve' (a Cross TOP crossfade), 'luma_wipe' (a Ramp-gradient-driven moving edge via GLSL), 'slide' (B pushes in from the right over A), 'zoom' (B scales in over A), or 'glitch_cut' (a hard A→B switch at 0.5 with a brief RGB-split tear). Progress 0 = full A, 1 = full B. Exposes live 'Progress' + 'Duration' knobs; drive Progress from manage_cue / bind_to_channel to run the transition on a beat or cue. Output is a Null ready for post-processing or setup_output. Returns a summary plus a JSON block with the container path, created node paths, the output path, exposed controls, any node errors, warnings, and an inline preview image.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoName for the transition system COMP.transition
parent_pathNoWhere to build it./project1
source_aNoTOP path for the A (outgoing) look. Omitted → a built-in test source (Constant/ramp) so it previews standalone.
source_bNoTOP path for the B (incoming) look. Omitted → a contrasting built-in test source.
styleNoTransition style: dissolve (crossfade), luma_wipe (gradient-driven edge), slide (B pushes A), zoom (B scales in), glitch_cut (RGB-shift hard cut).dissolve
progressNoInitial transition position 0=full A, 1=full B (exposed as a live knob).
durationNoSeconds for an auto Progress sweep when triggered (exposed as a knob; the knob can also be driven by manage_cue/bind_to_channel).
resolutionNoOutput resolution [w,h].
Behavior5/5

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

Descriptions aligns with annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) and adds behavioral details: it creates nodes, uses Select TOPs or built-in test sources, exposes live knobs, and returns comprehensive output including errors and preview. No contradictions.

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?

At ~120 words, the description is informative but somewhat lengthy. It is a single paragraph that efficiently conveys purpose, usage, and output, though breaking into bullet points could improve readability.

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?

Given no output schema, the description fully accounts for the return value: summary, JSON block with paths, controls, errors, and preview. It also covers prerequisites, configuration, and integration points, making it self-contained for an AI agent.

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?

Despite 100% schema coverage, the description adds value by explaining default behaviors (source omission triggers built-in tests), elaborating each style's implementation (Cross TOP, GLSL, etc.), and clarifying progress/duration roles. This goes beyond the schema's minimal descriptions.

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 clearly specifies the tool creates a parameterized A→B transition, the executable core of VJ cutting. It details the structural components (baseCOMP, sources, five styles) and how it integrates with other tools (manage_cue, bind_to_channel), making it distinct from sibling creation tools.

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 explains where the transition is built (parent_path), how to use it (drive Progress from manage_cue/bind_to_channel), and the available styles. While it doesn't explicitly state when not to use it, the context is clear enough for proper selection among many siblings.

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/Pantani/tdmcp'

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