Skip to main content
Glama

Map the Godot project

godot_scan
Read-onlyIdempotent

Maps a Godot 4 project from files without running the engine, covering scenes, scripts, signals, exports, autoloads, input actions, settings, and broken refs. Inspect structure before edits.

Instructions

Map a Godot 4 project from its files, without running Godot: scenes with node trees, scripts with class_name, signals, functions and exports, autoloads, input actions, key settings, and broken references. Call this first in a project, and again after large changes. For one name use godot_usages; for engine classes use godot_api. detail brief gives one line per scene and script; full adds node trees with line numbers, signal connections, input events and settings. Read-only. Returns an error when there is no project.godot at or above path.

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": "godot_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoproject folder, or a file or folder inside it (relative to the server's folder; default: the current project)
detailNobrief (capped lists) or full (everything); default full

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.0
    • changedInput schema / properties / detail / description
      Previous value: -"brief: short output with capped lists; full: everything (default for this premium profile: full)."New value: +"brief (capped lists) or full (everything); default full"
    • changedInput schema / properties / path / description
      Previous value: -"The project folder, or any file or folder inside it (Godotwright walks up to project.godot). Relative paths start at the server's folder. Default: the current project."New value: +"project folder, or a file or folder inside it (relative to the server's folder; default: the current project)"
  2. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / detail / description
      Previous value: -"Output detail (default for this premium profile: full)."New value: +"brief: short output with capped lists; full: everything (default for this premium profile: full)."
    • changedInput schema / properties / path / description
      Previous value: -"Project directory or a path inside it (default: the current project)."New value: +"The project folder, or any file or folder inside it (Godotwright walks up to project.godot). Relative paths start at the server's folder. Default: the current project."
  3. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the description's "Read-only" is redundant but harmless. It adds genuine behavior beyond the annotations: it operates statically without invoking Godot, it documents the failure mode (error when no project.godot at or above `path`), and it explains what the two detail levels actually return. It doesn't cover cost/latency on large projects, which keeps it off a 5.

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 verb and scope, then the payload list, then routing to siblings, then the detail semantics and error case — a sensible priority order with no filler. The long enumerations in the first sentence and the detail clause make it dense but each element carries information.

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?

There is no output schema, so the description must convey the return shape, and it does at a category level (scenes, scripts, autoloads, input actions, settings, broken references) plus the granularity difference between detail levels. For a two-parameter read-only mapping tool this is close to sufficient; exact field names and output size on large projects remain unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3; the description earns above that by expanding `detail` past the schema's thin "brief (capped lists) or full (everything)" into concrete contents — brief as one line per scene and script, full as node trees with line numbers, signal connections, input events and settings. It also clarifies that `path` is resolved upward for project.godot, which sharpens behavior beyond the schema's description.

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?

States a specific verb and resource ("Map a Godot 4 project from its files") and immediately enumerates what gets mapped: scenes with node trees, scripts with class_name, signals, functions, exports, autoloads, input actions, settings, broken references. That enumeration separates it cleanly from godot_api (engine classes) and godot_usages (one name), so an agent can route without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit timing ("Call this first in a project, and again after large changes") and names two alternatives with the condition that selects each ("For one name use godot_usages; for engine classes use godot_api"). Both when-to-use and when-not-to-use are covered.

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