Skip to main content
Glama

fusion_comp_info

Inspect a Fusion composition's tools and wiring, or query a specific tool's input values and hidden advanced settings; target the current Fusion page clip or a timeline clip.

Instructions

Inspect a Fusion comp: tools (name, type, inputs wired from which tool). With tool_name: that tool's inputs (id, name, type, current value) — filter with search; all_inputs=true includes hidden/advanced ones. clip: timeline clip ref, or 'current' (comp open on the Fusion page).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "fusion_comp_info"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNocurrent
compNo
searchNo
tool_nameNo
all_inputsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the shape of what is returned (tool names, types, and which tool each input is wired from) plus the meaning of the hidden-input flag. It never states that the operation is read-only/non-mutating, nor how it behaves when the target comp doesn't exist, which are meaningful gaps for an unannotated tool.

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?

Content is front-loaded and dense: the primary mode is stated first, then the tool_name variant, then the clip reference convention. The telegraphic, fragment-heavy style saves tokens but occasionally reads like notes rather than prose; nothing is redundant.

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 read-only inspection tool with five undocumented parameters and no output schema, the description supplies enough to make a first correct call in the common case. It falls short on the unexplained `comp` parameter, the clip-vs-comp interaction, and failure behavior, so an agent still has to guess at the edges.

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 compensate, and it does cover four of five parameters: clip (timeline ref or 'current'), tool_name (mode switch), search (filter), and all_inputs (include hidden/advanced). The `comp` parameter, however, is never mentioned and its relationship to `clip` is left ambiguous, which is a real cost at 0% schema coverage.

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?

"Inspect a Fusion comp" is a specific verb+resource, and the description clearly enumerates two operating modes: default (list tools with name, type, and wiring) and tool_name-scoped (that tool's inputs with values). It does not explicitly differentiate itself from sibling inspection tools like fusion_comps or clip_info, so the agent must infer that boundary.

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

Usage Guidelines3/5

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

It gives usable conditional guidance: pass tool_name for per-input detail, add search to filter, set all_inputs=true to include hidden/advanced inputs, and use clip='current' for the open comp. What's absent is any statement of when to pick this over sibling tools or what happens if the comp/clip reference is invalid.

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