Skip to main content
Glama
Beckett — MCP for Godot

Beckett — MCP for Godot

by beckettlab

instance_scene

Instance packed .tscn/.scn files or imported models as child nodes in the open Godot scene, keeping editor-style file links so later source edits appear. Undoable.

Instructions

Instantiate a packed scene (res://*.tscn, or an imported model such as .glb) as a child in the open scene (undoable). It instances the scene the way the editor does, so the saved scene stores it as an instance of the file and later edits to the file show up in this scene.

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": {
      "scene": "<scene>"
    },
    "name": "instance_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
sceneYesres:// path to a .tscn/.scn, or an imported model such as .glb
parentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.0
    • changedInput schema / properties / scene / description
      Previous value: -"res:// path to a .tscn/.scn"New value: +"res:// path to a .tscn/.scn, or an imported model such as .glb"
  2. Addedv1.12.1
  3. Removedv1.10.1
  4. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare this is a non-readonly, non-destructive, non-open-world mutation, and the description adds real value beyond them: the operation is undoable and it replicates editor instancing semantics, so the saved scene stores a file reference and later edits to the source file propagate (inherited scene behavior). That propagation detail is non-obvious and materially affects an agent's decision. It stops short of stating failure modes or the return value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, with the action and target front-loaded and the inheritance consequence following. Every clause carries information an agent needs.

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 3-parameter mutation tool with no output schema and only 33% schema coverage, the description covers the core action well but leaves gaps: what it returns (node path?), how `name` defaults, what `parent` defaults to, and what happens if no scene is open. Adequate, not complete.

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 33% — only `scene` is documented, and the description mostly restates it (res:// path, .tscn/.glb). It adds a little on `parent` by saying the result lands 'as a child in the open scene,' implying a default parent, but `name` (and default naming) is undocumented in both places.

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 (instantiate) and resource (packed scene: .tscn/.scn/.glb) plus the target location (as a child in the open scene). It does not explicitly differentiate itself from siblings like create_node, open_scene, or duplicate_node, but the resource-type framing implicitly separates it.

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?

Usage is only implied: the tool requires an already-open scene and adds a child to it. There is no explicit when-to-use guidance, no mention of create_node/duplicate_node as alternatives, and no statement about what happens when no scene is open or how it differs from opening a scene directly.

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