Skip to main content
Glama

search_objects

Read-onlyIdempotent

Search about 100k 3D objects by English visual description or exact keywords. Returns object IDs plus a numbered contact sheet to pick the right model.

Instructions

Search the Sand3D catalog (about 100k 3D objects with GLB, render and generating Python program, CC BY 4.0). Default mode compares an English text description with the renders (CLIP), so describe the look in English, e.g. 'old red farm tractor'. match_words=true does exact keyword search in names, families, attribution and program code. Returns a numbered text list with object ids and a contact sheet image with the same numbers; names repeat a lot, so pick by the image. 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

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": "search_objects"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many results to return (1-200).
queryNoEnglish description of the object, or keywords when match_words=true. Empty lists the catalog with filters.
familyNoFamily key or label inside the dataset (needs dataset), e.g. 'musical instrument'.
offsetNoSkip this many results (pagination).
datasetNoLimit to one dataset: objaverse, cad, articraft, simready, automate. See list_datasets.
match_wordsNoExact keyword search instead of visual meaning search.
contact_sheetNoAttach a numbered contact sheet JPEG of the renders (about 100-380 KB).
assembly_partsNoSearch individual parts of AutoMate assemblies.
only_with_jointsNoOnly articulated objects (doors, wheels, levers that move).
include_without_glbNoAlso return objects that have no GLB (only USDA).

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?

Annotations already declare read-only, idempotent, open-world, non-destructive, but the description adds substantial context beyond them: it discloses the backend is a free single-CPU space, that this is fine for dozens of objects but not bulk work, and exactly what is returned (a numbered text list of object ids plus a numbered contact-sheet image). The warning that names repeat so selection should be visual is a genuinely useful behavioral caveat.

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?

Dense but front-loaded: catalog identity and default mode come first, then the alternate mode, then return shape, then performance limits. Every sentence carries information, though the contact-sheet size detail partially duplicates the schema's contact_sheet description.

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?

With 10 parameters and no output schema, the description does the necessary work: it explains the return format, both search modes, and the performance envelope. Nothing critical for correct first-call invocation 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 baseline is 3, but the description adds real meaning: it explains that query is an English appearance description in default mode versus exact keywords when match_words is true, and that match_words searches names, families, attribution and program code specifically. That exceeds what the schema's terse parameter descriptions convey.

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 and resource ('Search the Sand3D catalog, about 100k 3D objects') and immediately distinguishes its two operating modes (default CLIP visual-text matching vs. match_words exact keyword search). An agent can tell what this does and what it returns without opening any schema.

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 clear guidance on mode selection: describe the look in English for default mode, use match_words=true for keyword search over names/families/attribution/program code, and for bulk work go to the open Hugging Face datasets instead. It also advises picking by the contact sheet because names repeat. It stops short of routing to siblings like find_similar or get_object for follow-up lookups.

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