Skip to main content
Glama

asset_search

Read-only

Searches ready-made 3D models, PBR textures, and HDRIs from multiple libraries with filters for kind, license, size, and category; returns asset IDs and optional previews for import.

Instructions

Searches ready-made 3D assets on the internet: models, PBR textures, HDRIs. source: all (default, in parallel), polyhaven (all CC0, no key), ambientcg (textures/hdris, CC0), sketchfab (models; a token is needed to download), polypizza (low-poly models; an API key). The query is English ('couch' also finds sofa). kind: model, texture, hdri. license: CC0 only by default; 'cc0,by' also brings CC-BY (attribution required). category: a text filter. polyhaven only: attrs={'weather': 'clear'} (hdri), min_size_m (the real size of a texture; 2+ for floors and walls). max_faces: polygon cap (polyhaven, sketchfab). animated: sketchfab, polypizza. previews=N (at most 6): small images of the first N results as one numbered image. Line: source id | kind | name | category | faces | size (m) | highest resolution | license | author. Pass the id to asset_import.

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": "asset_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
attrsNo
limitNo
queryNo
sourceNoall
licenseNocc0
animatedNo
categoryNo
previewsNo
max_facesNo
min_size_mNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint, it discloses that source=all queries providers in parallel, that previews is capped at 6 and returned as one numbered image, and the exact result-line format (source id | kind | name | category | faces | size | resolution | license | author). The credential requirements for downstream download are surfaced before the agent commits.

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?

Nearly every clause carries new information, and the purpose is front-loaded before the parameter notes. Readability suffers from being a dense run-on with an awkward line break ('ambientcg\n(textures/hdris'), which a short bulleted structure would fix without adding length.

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?

For an 11-parameter, keyless-search tool with no output schema, the description covers the result format, licensing, and credential implications well. The gaps are the undocumented limit parameter and no statement of pagination or behavior when zero results match.

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?

With 0% schema description coverage across 11 parameters, the description carries the full burden and defines almost all of them: query language behavior ('couch' also finds sofa), kind values, license values, source values, polyhaven-only attrs and min_size_m, max_faces, animated, and previews. The exception is limit, which is never mentioned, leaving result-count control undocumented.

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?

Opens with a specific verb and resource: 'Searches ready-made 3D assets on the internet: models, PBR textures, HDRIs.' It also marks the boundary with the follow-up tool by stating 'Pass the id to asset_import,' so the agent knows this is discovery, not download.

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?

Gives concrete selection guidance per source (polyhaven is CC0 and keyless, sketchfab needs a token to download, polypizza needs an API key) and explains the license default ('CC0 only by default; cc0,by also brings CC-BY'). It stops short of saying when to prefer this over sibling api_search, but the per-source conditions are actionable.

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