Skip to main content
Glama

ai_modeling_asset_download

Download existing Studio or Canvas assets—images, models, motions, UV layouts, segmentation previews, and Lab artifacts—to a chosen path using exact source IDs; no generation or export is created.

Instructions

Download an existing Studio or Canvas asset, a template image shown by the webpage, exact applied motion, segmentation preview, Lab file/input representation or UV layout to a caller-selected path. Creates no generation or export task; requires the exact source context. Segmentation previews are normalized images, not original-image pixel masks.

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": {
      "kind": "<kind>",
      "id": "<id>",
      "destination_path": "<destination_path>"
    },
    "name": "ai_modeling_asset_download"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
kindYes
job_idNoRemote Lab job ID for lab_artifact or lab_input; not a local CLI job ID.
node_idNoExact source node, required for canvas_input, canvas_node and template_image.
canvas_idNoSource saved Canvas, required for canvas_input.
operator_idNoExact model version or applied motion; required for motion, uv_layout and segmentation_preview.
template_idNoSource Canvas template, required for template_model or template_image.
output_indexNo
destination_pathYes
current_operator_idNoOriginal UV context model version, required for uv_layout.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=false and openWorld=true, so the write-to-disk nature is partly covered. The description adds real value with the caveat that segmentation previews are normalized images rather than pixel masks, but it says nothing about overwrite behavior at destination_path, parent-directory creation, or permission/auth requirements — notable for a tool flagged non-destructive that writes to a caller-chosen path.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and the resource list, with the two most decision-relevant facts (no task creation, normalization caveat) placed at the edges. Nothing is redundant with the title or the schema.

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

Completeness3/5

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

For a 10-parameter, kind-driven tool with conditional requiredness and no output schema, the description covers what can be downloaded and one output-content caveat, but not the conditional parameter matrix or what is returned on success. An agent could pick the wrong kind/context combination without opening the schema in detail.

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

Parameters3/5

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

Schema coverage is 60%, so several parameters (destination_path, output_index, canvas_node, and the base id/kind interplay) are undocumented in the schema. The description reinforces 'caller-selected path' and sketches the asset kinds that the 'kind' enum encodes, but it does not explain the per-kind conditional requirements (job_id for lab_*, operator_id for motion/uv_layout/segmentation_preview, canvas_id+node_id for canvas_input) that dominate this schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb (Download) and enumerates the resource classes it covers (Studio/Canvas asset, template image, applied motion, segmentation preview, Lab file/input, UV layout), which maps well onto the 'kind' enum. It stops short of naming its closest sibling, ai_modeling_artifact_download, so an agent must still infer which of the two download tools applies.

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?

'Creates no generation or export task' rules out the export-style tools, and 'requires the exact source context' implies prerequisites, but neither is framed as a when-to-use/when-not rule. There is no explicit routing statement such as 'for generated artifacts use artifact_download instead', leaving sibling selection to inference.

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

Deploy Server

Other Tools