Skip to main content
Glama

fusion_set

Set static, animated, connected, or expression-driven inputs for a Fusion tool. Define values, keyframes, node connections, and expressions to control a composition.

Instructions

Set inputs of a Fusion tool. Static: {"Size": 0.1, "Center": [0.5, 0.3], "StyledText": "سلام"}. Animated: {"Size": {"keyframes": [[0, 0.05], [1.5, 0.12]]}} — times in seconds from the comp start ('12f' for frames); creates a spline (points use a path). ease: linear | smooth (default Fusion bezier). Connect: {"Input": {"connect": "Blur1"}}. Expressions: {"Angle": {"expression": "time*2"}}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tool_name": "<tool_name>",
      "inputs": "<inputs>"
    },
    "name": "fusion_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNocurrent
compNo
easeNo
inputsYes
tool_nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden. It does strong work on value encoding — static vs keyframed values, time units in seconds or '12f', ease modes, and expression strings — but says nothing about overwrite semantics, whether existing inputs are replaced, permissions, or failure modes for a nonexistent tool_name.

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 compact labelled examples that each earn their place. It is terse to the point of being cryptic in places (bare inline JSON, a stray Persian sample string), but there is little waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter, nested-object mutation tool with no annotations and no output schema, the payload documentation is good but the addressing parameters (clip, comp, tool_name) and any response/error behavior are undocumented, leaving real gaps for correct invocation.

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?

Schema coverage is 0%, so the description must compensate, and it does so only for 'inputs' (thoroughly) and partially for 'ease' ('linear | smooth (default Fusion bezier)'). The clip, comp, and tool_name parameters get no explanation at all, including their 'current'/null defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Set inputs of a Fusion tool.' An agent can tell this mutates tool input values. It does not explicitly distinguish itself from siblings like fusion_connect or fusion_tool_add, and the Connect example actually blurs the line with fusion_connect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The text is almost entirely payload syntax documentation; it never says when to use fusion_set versus fusion_connect, whether the target tool must already exist, or whether a comp must be open. The only implicit routing hint is that connection inputs can be set directly here via {"connect": "Blur1"}.

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