Skip to main content
Glama

find_similar

Read-onlyIdempotent

Find visually similar Sand3D objects by object ID and return a numbered list with an optional contact sheet image for quick comparison.

Instructions

Find objects that look like a given Sand3D object (visual nearest neighbours). Returns a numbered list and a contact sheet 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

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>"
    },
    "name": "find_similar"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many results to return (1-200).
object_idYesObject id from search_objects, e.g. 'objaverse-d1147d567cf84d569c1abec10301cd29'.
same_datasetNoOnly look in the same dataset as the given object.
contact_sheetNoAttach a numbered contact sheet JPEG of the renders (about 100-380 KB).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds real value on top: the output shape (numbered list plus contact sheet image) and the compute/capacity profile of the free single-CPU space. It stops short of stating expected latency or whether similarity scores are returned.

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 sentences, front-loaded with the core action, then return shape, then capacity guidance. No filler and nothing repeated from the annotations or schema.

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?

With no output schema, the description usefully states what comes back (numbered list and contact sheet JPEG). For a read-only search tool with fully documented parameters this is nearly complete, missing only detail on whether results carry similarity scores or distances.

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 description coverage is 100%, so limit, object_id, same_dataset and contact_sheet are all documented in the schema itself. The description mentions the contact sheet only as a return artifact, not as a toggle, and adds no new semantics for limit or same_dataset; baseline 3 applies.

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?

States a specific verb and resource — find objects visually similar to a given Sand3D object — and clarifies the mechanism as 'visual nearest neighbours', which distinguishes the operation from keyword lookup via search_objects. It does not name the sibling outright, so the differentiation is inferable rather than explicit.

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 clear scale-based usage rule: fine for dozens of objects on the free single-CPU space, but for bulk work switch to the Hugging Face datasets Sandflow/sand3d-*. It does not say when NOT to use this at all (e.g. exact-match or metadata queries), so there is no full exclusion set.

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