Skip to main content
Glama

ai_modeling_canvas_upload

Upload an image, 3D model, or Lab video to a Canvas project, with optional model transform, UV preservation, and readiness wait.

Instructions

Upload an image, model or Lab video to a Canvas project. Model imports support a transform and UV preservation; optionally wait for the accepted input asset to become ready. No node is added automatically.

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": {
      "project_id": "<project_id>",
      "file_path": "<file_path>"
    },
    "name": "ai_modeling_canvas_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_pathYes
project_idYes
wait_secondsNoWait up to this many seconds for the registered input asset; 0 returns its actual initial status.
transformationNoModel import transform as 16 column-major numbers; omitted means the unrotated identity matrix.
use_original_uvNoPreserve model UVs as the Canvas Upload Card does (default true). Model inputs only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare the write/open-world/non-destructive profile, and the description adds real context beyond them: no node is created as a side effect, model imports support a transform and UV preservation, and the call can optionally block until the asset is ready. Missing are practical traits such as supported file formats, size limits, and whether re-uploading the same file is idempotent.

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 tight sentences: action and accepted types first, then the model-import options, then the optional wait and the no-node caveat. Every clause carries information an agent needs, with no filler or restated field names.

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 mutating, open-world upload with five parameters and no output schema, the description covers what is uploaded and the model-specific options, but does not say what comes back (asset identifier, status, or path) or how failures surface. Combined with the undocumented project_id/file_path, an agent still has gaps before it can chain this call into asset_select or bind_lab.

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 60% (wait_seconds, transformation, use_original_uv documented; project_id and file_path bare but self-evident). The description adds meaning beyond the schema by tying the transform and UV behavior specifically to model imports, clarifying that these options do not apply to image or Lab video uploads.

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?

Specific verb plus resource and accepted input types: 'Upload an image, model or Lab video to a Canvas project.' The closing 'No node is added automatically' sharply delimits the scope against sibling tools like canvas_graph_edit or canvas_node_assets, so an agent can tell what this tool will and will not do without opening the schema.

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?

Usage is only implied: upload precedes asset_select/bind_lab, and 'optionally wait for the accepted input asset to become ready' hints at a downstream readiness workflow. There is no explicit when-to-use statement, no prerequisite (project must exist, file must be local), and no named alternative for any overlapping case.

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