Skip to main content
Glama

fusion_comps

Manage Fusion compositions for a timeline item: list, add, import, export, load, rename, or delete comps by index or name for DaVinci Resolve workflows.

Instructions

Fusion compositions of a timeline item: list, add a new one, import a .comp, export one (by 1-based index) to a .comp, load (make active), rename or delete by name. The comp itself is reachable as 'comp::<index|name>' with call_api / execute_python (Fusion API).

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": {
      "item": "<item>",
      "action": "<action>"
    },
    "name": "fusion_comps"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYes
nameNo
pathNo
indexNo
actionYes
new_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior1/5

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

Annotations declare destructiveHint=false and readOnlyHint=false, yet the description explicitly offers a 'delete' action (and 'load (make active)' state changes), which is a destructive mutation. The description is the accurate party here, but the definition as a whole contradicts its structured safety signals, so an agent trusting the annotations would underestimate risk. Useful extras (1-based index, .comp path semantics, comp: addressing) do not offset that conflict.

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?

Two dense sentences, front-loaded with the operation list and followed by the addressing/alternate-access note; almost nothing is wasted. The packed parentheticals make it slightly harder to parse than a short bulleted action map would be.

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 seven-action tool with six undocumented parameters and no output schema, the description covers operations and addressing but leaves per-action parameter requirements, return values (e.g. what list yields, what export produces), and error/precondition behavior unstated. Adequate to attempt a call, not sufficient to call confidently for every action.

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 description coverage is 0%, so the description must carry all parameter meaning. It partially does: index is 1-based and used for export, name selects rename/delete targets, path binds to .comp import/export, and item is the timeline item. It never explains what 'add' requires (name? new_name?), how name and new_name differ for rename, or the expected format of item (uid vs handle) and path.

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 names a specific resource (Fusion compositions of a timeline item) and enumerates every operation the action enum supports: list, add, import, export, load, rename, delete. It also states the addressing scheme 'comp:<item uid>:<index|name>' and points to call_api/execute_python for work on the comp itself, which distinguishes it from generic API 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?

It tells the agent which operations exist and maps key ones to the right selector ('export one (by 1-based index)', 'rename or delete by name'), and routes deeper comp manipulation to call_api/execute_python. It does not explicitly exclude or compare against the sibling get_fusion_comp, and it never says when to prefer this tool over raw Fusion API calls for simple reads.

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

Deploy Server

Other Tools