Skip to main content
Glama
Beckett — MCP for Godot

Beckett — MCP for Godot

by beckettlab

get_remote_tree

Read-only

Dumps the running game's live scene tree with path, depth, and node-limit scoping, so you can inspect runtime nodes without exceeding token budgets.

Instructions

Dump the live scene tree of the RUNNING game (runtime counterpart of get_scene_tree). SCOPE IT to stay under token limits — a full game tree blows the budget. path=subtree root (name, relative, or absolute /root/...); depth=levels (-1=all); max_nodes (default 250); max_children per node (default 50); collapse=true groups runs of identical leaf siblings (e.g. '8x CPUParticles2D'); state=true adds game-owned state (help(tool="get_remote_tree")). Returns {tree, node_count, truncated?}.

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": "get_remote_tree"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
depthNo
stateNo
collapseNo
max_nodesNo
max_childrenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.0
    • addedInput schema / properties / state
      Added value: +{
      +  "type": "boolean"
      +}
  2. Addedv1.12.1
  3. Removedv1.10.0
  4. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/non-destructive/closed-world, so the description correctly focuses on what they cannot convey: token-budget pressure, truncation behavior, and the returned shape {tree, node_count, truncated?}. It adds real value, though it doesn't say what happens on error or when the game isn't playing.

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 purpose and the scoping warning, then parameter notes, then return shape — a sensible order. The telegraphic semicolon packing is efficient but dense enough that readability suffers slightly.

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

Completeness4/5

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

Six parameters at 0% schema coverage are all explained, defaults are given, and the return shape is stated despite no output schema. The main omission is preconditions (game must be running / how to verify) and error behavior on an invalid path.

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?

Schema description coverage is 0%, so the description carries the full burden and does: path semantics (name, relative, or absolute /root/...), depth=-1 meaning all levels, defaults for max_nodes (250) and max_children (50), and the semantics of collapse with a concrete '8x CPUParticles2D' example and state. This is meaningfully richer than the bare schema.

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?

Specific verb+resource: 'Dump the live scene tree of the RUNNING game'. It explicitly positions itself as the runtime counterpart of get_scene_tree, which is a named sibling, so the agent can distinguish the two without inspecting schemas.

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?

States the operative constraint ('SCOPE IT to stay under token limits — a full game tree blows the budget') and implies use only when the game is running, with get_scene_tree as the editor-side alternative. It does not say what to do if no game is running (e.g. check get_play_state first), which keeps it from a 5.

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