Skip to main content
Glama

Search objects

search_objects
Read-only

Search the obbjects catalog of isolated object images on a plain white background. Returns matches with image_url (1024px square WebP on white), transparent_png_url (same image with a transparent background, for placing on colored slides or pages; null if the object has none), thumbnail_url, license and attribution. Each result has match 'full' (all words matched) or 'partial'. When nothing matches fully, the response has a note and you can call request_object. Use short noun phrases like 'coffee mug' or 'red ball'. To browse, leave query empty and set category (and optionally color): you get that category's objects, newest first, up to limit.

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
colorNoDominant color word, e.g. 'red'
limitNo
queryNoWhat object you need, e.g. 'coffee mug'. Leave empty to browse a category
categoryNoExact category from list_categories; alone, it lists that category

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / category / description
      Previous value: -"Exact category from list_categories"New value: +"Exact category from list_categories; alone, it lists that category"
    • changedInput schema / properties / query / description
      Previous value: -"What object you need, e.g. 'coffee mug'"New value: +"What object you need, e.g. 'coffee mug'. Leave empty to browse a category"
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond readOnlyHint and openWorldHint=false, the description discloses concrete behavior: exact return fields including the nullable transparent_png_url, per-result match status of 'full' or 'partial', the presence of a note when nothing matches fully, and that browse results come newest-first up to limit. It does not discuss pagination beyond the limit cap or rate limits, keeping it short of a 5.

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-loaded with purpose, then returns, then match status, then usage modes; nearly every clause carries information an agent needs to pick and call the tool. It is dense and reads as a run-on, and the typo 'obbjects' slightly mars an otherwise tight block.

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 no output schema, the description takes on the burden of describing results and does so fully: URLs and their formats, licensing fields, match quality, and the empty-result note. Combined with annotations covering the read-only, closed-world safety profile, nothing an agent needs to call it correctly 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 75%, and the description adds real meaning on top: the interaction between query and category (empty query + category = browse), that color is an optional narrowing in browse mode, and that results are capped 'up to limit'. The one gap is that limit's own semantics (default 10, max 50) are left to the schema.

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 a catalog of isolated object images on a plain white background, and enumerates the returned fields. It is clearly distinguishable from get_object and list_categories by being the query/browse entry point, and it names request_object as the fallback path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit query-formulation advice ('short noun phrases like coffee mug'), an explicit browse mode (empty query + category, optional color), and an explicit alternative to invoke when nothing matches fully (request_object). Mode selection and fallback routing are both spelled out rather than inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources