Skip to main content
Glama

download_object

Idempotent

Download a Sand3D object's GLB, render, metadata, and source files into a chosen folder, with optional USDA and three.js joint helper outputs.

Instructions

Download one Sand3D object into a folder the user chose: model.glb, program.py, render.png (512x512, transparent) and meta.json with license and attribution; model.usda too when include_usda=true or when the object has no GLB. Files go to /; existing files with the same names are overwritten. Returns paths, sizes, GLB stats (meters, Y up), part names, joints and the attribution string to credit (CC BY 4.0). include_threejs_helper=true also writes s3d-joints.js (collectJoints, setJoint, setJoint01, fitToHeight). Only writes inside the given directory. Runs against a free single-CPU space by Sandflow: fine for dozens of objects; for bulk work use the open Hugging Face datasets Sandflow/sand3d-*.

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": {
      "object_id": "<object_id>",
      "directory": "<directory>"
    },
    "name": "download_object"
  }
}

Input Schema

NameRequiredDescriptionDefault
directoryYesTarget root folder, absolute path or relative to the client's working folder, e.g. 'assets/sand3d'. Ask the user if unsure.
object_idYesObject id from search_objects or find_similar.
subfolderNoSubfolder name inside directory. Default is '<name-slug>-<hash>' from the object name.
include_usdaNoAlso download model.usda from the Hugging Face dataset.
include_threejs_helperNoAlso write s3d-joints.js, a three.js helper for joints and scaling.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: explicit overwrite semantics for same-named files, a write-scope guarantee ("Only writes inside the given directory"), throughput limits of the free single-CPU backend, and a licensing obligation to surface the CC BY 4.0 attribution string. It also documents the concrete return payload (paths, sizes, GLB stats in meters with Y up, part names, joints).

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-loads the action and the file manifest, then layers side effects and limits. It is a dense semicolon-chained paragraph, which is efficient but makes the overwrite warning and the attribution requirement slightly easy to skim past; splitting those into their own sentences would help.

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 multi-artifact download tool with no output schema, the description covers the files written, the destination layout, overwrite risk, the return contents, licensing, and scale limits. Nothing an agent needs in order to call it safely is missing.

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 the baseline is 3, but the description earns above baseline by explaining a conditional the schema cannot: model.usda is downloaded when include_usda=true OR when the object has no GLB. It also spells out what include_threejs_helper produces (s3d-joints.js with collectJoints, setJoint, setJoint01, fitToHeight) and that subfolder defaults from the object name plus hash.

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 ("Download one Sand3D object into a folder the user chose") and immediately enumerates the exact artifacts produced (model.glb, program.py, render.png, meta.json, optional model.usda). The object_id provenance reference ("from search_objects or find_similar") makes it clearly a terminal fetch step distinct from the discovery siblings.

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 a real exclusion: for bulk work, use the open Hugging Face datasets instead of this tool, since it runs on a free single-CPU space. It also frames the directory parameter around user intent, but does not say when to prefer get_object (metadata/preview) over a full download, so guidance is clear context rather than a complete decision tree.

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