Skip to main content
Glama

api_manage

Retrieve class reference sections from the Godot API—properties, methods, signals, enums, and constants—without creating scene instances.

Instructions

Inspect Godot API documentation-shaped metadata from the connected editor's ClassDB: "what properties does X have", method signatures, signals, enums, constants, defaults, and property hint strings.

Resource form (prefer for active-session reads): godot://class/{class_name}

Ops:

  • get_class(class_name, sections=None, include_inherited=False, include_inheritors=False, offset=0, limit=100) Return selected class-reference sections without creating a scene instance. sections may be a comma-separated string or list containing properties, methods, signals, enums, constants, inheritors. Defaults to ["properties"] only — a bare get_class answers "what properties does X have" without the multi-thousand-token full dump. Pass the sections you want by name, or "all" for the full set (properties, methods, signals, enums, constants). "all" does NOT include the heavier "inheritors" section — request that by name. For pagination, request one section at a time so offset/limit apply only to the list you are paging.

Canonical call shape: {"op": "<verb>", "params": {...}}. Flat op parameters are accepted as a compatibility alias when the client transmits them; op and session_id remain top-level.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYes
paramsNo
session_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

With no annotations, the description covers behavioral details: default sections, pagination behavior (offset/limit per section), and that 'all' excludes inheritors. However, it does not explicitly state the tool is read-only or non-destructive.

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?

Well-structured with purpose upfront, followed by operation details and call shape. Some redundancy (e.g., repeating default sections) but every sentence adds value. Slightly verbose but still efficient for the information density.

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

Completeness5/5

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

Given the complexity (multiple operations, pagination, output schema exists), the description covers purpose, parameters, usage patterns, and pagination advice comprehensively. No significant gaps for a read-only documentation inspector.

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?

Despite 0% schema coverage, the description thoroughly explains the op, params structure, sections argument details (defaults, 'all', comma-separated list), pagination parameters, and flat parameter compatibility. Adds significant meaning beyond the minimal 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?

Clearly states the tool inspects Godot API documentation-shaped metadata from ClassDB, with examples like 'what properties does X have' and specific operations. Distinguishes from sibling tools like node_manage that handle runtime objects.

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?

Provides detailed call examples and pagination advice, but does not explicitly state when to use this tool vs alternatives (e.g., node_manage for runtime node inspection). Usage context is implied through purpose but lacks direct guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hi-godot/godot-ai'

If you have feedback or need assistance with the MCP directory API, please join our Discord server