Skip to main content
Glama

Asset library: ready-made base recipes

godot_model_library
Read-onlyIdempotent

Search over a thousand ready-made 3D asset specs by query, category, family, or id, then inspect parameters and full JSON before building clean, lint-checked GLB models.

Instructions

Search the asset library: over a thousand ready-made base recipes (furniture, street furniture, storage and industrial props, nature, buildings, vehicles, props), each a model spec with parameters that builds a clean, lint-checked .glb. With nothing: an overview per category and family. With query (English or Dutch words, e.g. 'oak chair', 'rode bank', 'pine tree') and/or filters: matching assets, one line each. With id (e.g. furniture/dining-chair-oak-ladder): what it is, its parameters, materials and parts; with spec: true the full spec JSON to copy, change and pass to godot_model_build as spec. Build one as is with godot_model_build kind: <id> and params. Start here before writing a spec from scratch. Read-only.

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_model_library"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoan asset id to show, e.g. furniture/dining-chair-oak-ladder
specNowith `id`: return the full spec JSON
limitNoat most this many results (default 30)
queryNowords to search for, English or Dutch
familyNoonly this family, e.g. dining-chair
categoryNoonly this category: furniture, street, storage, nature, buildings, vehicles or props
archetypeNoonly assets of this archetype or below it, e.g. prop.chair

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.8.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so "Read-only" is redundant, but the description goes further by describing per-mode behavior: an overview per category and family with nothing, one line per match with query/filters, and identity/parameters/materials/parts with id. It also discloses that assets build clean, lint-checked .glb files, which is real behavioral context. It does not describe pagination or result ordering, keeping it short of 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?

Structure mirrors the call modes (nothing / query+filters / id), which is easy to scan, and the discovery-first instruction is front-loaded. It is dense with parenthetical examples that partly duplicate the schema's own examples, so it is slightly longer than strictly necessary.

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?

For a seven-parameter, zero-required discovery tool with no output schema, the description covers what each mode returns, how results feed into godot_model_build, and the read-only nature of the operation. An agent can pick the right mode and chain to the build step without further information.

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 baseline would be 3, but the description adds meaning the schema does not: `query` accepts English or Dutch with concrete examples ('oak chair', 'rode bank', 'pine tree'), and the `id` + `spec: true` interaction is explained as producing JSON to copy and pass to godot_model_build. The example id format (furniture/dining-chair-oak-ladder) also clarifies the string shape beyond the schema's terse example.

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?

"Search the asset library" gives a specific verb + resource, and the description immediately qualifies what is being searched (over a thousand ready-made base recipes, each a model spec producing a lint-checked .glb). The three operating modes (no args = overview, query/filters = matching assets, id = full detail) make it distinguishable from sibling tools like godot_model_inspect or godot_model_spec.

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?

It states explicitly when to use it ("Start here before writing a spec from scratch") and routes the agent onward to godot_model_build with `kind: <id>` and `params`, including the copy-and-modify path via `spec: true`. The relationship between discovery and build is unambiguous.

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