Skip to main content
Glama

asset_import

Destructive

Downloads an allow-listed asset into a local cache and imports it into Blender as a sized model, Principled texture material, or new HDRI world, recording license and attribution.

Instructions

Downloads a found asset and brings it into Blender (the download happens on this computer, from allow-listed hosts, with a size cap, into a cache; it is not downloaded twice). model: arrives under a root empty; target_size = the largest dimension in metres (chair 1.0, car 4.5, cup 0.12; sketchfab/polypizza arrive at an arbitrary scale, always give it); snap_to_ground puts the centre of the base at location ([x, y, z], default 0,0,0). texture: a Principled material named 'source_id' (kept even if it is outside the scene); apply_to=['Object'] replaces those meshes' material (warns if there are no UVs). hdri: assigned as a new world (the old one is kept). resolution: 1k (default), 2k, 4k, 8k; format: model gltf/fbx, texture jpg/png, hdri hdr/exr. accept_license: take a non-CC0 asset knowingly. Returns: bounding box, tris, materials, file, license; look at it with view afterwards. The root gets the properties asset_source/asset_license/asset_attribution. A generated model: source='rodin' or 'hunyuan', id = the job from generate_start (it must be done: see generate_status); target_size is advisable.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "app": "<app>",
      "source": "<source>",
      "id": "<id>"
    },
    "name": "asset_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
appYes
kindNo
formatNo
sourceYes
apply_toNo
locationNo
resolutionNo1k
target_sizeNo
accept_licenseNo
snap_to_groundNo

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?

Goes well past the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) by disclosing what actually mutates: apply_to replaces those meshes' materials (and warns when there are no UVs), hdri becomes a new world while the old one is kept, and the root empty gains asset_source/asset_license/asset_attribution. It also discloses non-obvious infrastructure behavior — local download, allow-listed hosts, size cap, cache, no double download — and names the returned fields.

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 core action and the download constraints, and essentially every clause carries information (no filler). The downside is structure: it is one long run-on paragraph with nested parentheses and inline enumerations, which makes it slower to scan than a short bulleted breakdown of model/texture/hdri modes would be.

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, no-output-schema tool, the description is nearly sufficient: it covers all modes, the license caveat, side effects on the scene, and even enumerates the return payload so no output schema is needed. The unexplained required 'app' parameter is the one real hole.

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 burden and mostly succeeds: target_size units and example values, snap_to_ground meaning (centre of base at location), apply_to semantics, resolution/format enumerations, and the id/source pairing for generated jobs. The notable gap is 'app' — a required parameter that is never explained — and the empty-default 'kind' is only inferable from the model/texture/hdri sections.

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+resource: 'Downloads a found asset and brings it into Blender', and immediately scopes the download mechanics (local, allow-listed hosts, size cap, cache). It also carves out the generated-asset path (source='rodin'/'hunyuan' from generate_start), which separates it from the sibling generate_* tools.

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 usage context: target_size values with real examples (chair 1.0, car 4.5, cup 0.12), the note that sketchfab/polypizza arrive at arbitrary scale so target_size should always be given, accept_license for non-CC0 assets, and 'look at it with view afterwards'. It also routes generated models through generate_start/generate_status. It stops short of explicitly saying when NOT to use this tool versus asset_search, but the context is clear.

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