Skip to main content
Glama

Composition card

get_composition
Read-onlyIdempotent

Retrieves everything known about a light composition from its catalogue code, including names, family, type, localized texts, pages, images, 3D models, exports, awards, and configurator status.

Instructions

Everything the public dataset knows about one composition by its code (LC0564, lc0564, "564" are all accepted): names RU/EN, family and type, the brand's texts in the requested language (default en; ru de it fr es vi ar available), site pages in 8 languages, cover image, 3D models (3ddd/3dsky, Sketchfab), awards, whether it is certified (fact only), and the configurator status: opens with a full calculation or is calculated individually; kind (cloud of elements / ribbon / chain / on a frame / ready scene); IFC4, FBX, PDF and tender-sheet exports; whether the 1:1 ceiling drawing exists; ready links. For compositions of the ceramic collection, ceramic_collection gives the group and the page. No price and no composition dimensions — they are not published.

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": {
      "code": "<code>"
    },
    "name": "get_composition"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesCatalogue code, e.g. LC0564 or LC0406-1
langNoLanguage of the texts, default en

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and closed-world scope, so the safety profile is covered; the description adds real behavioral context on top: accepted code variants and normalization, default and available languages, which fields simply do not exist in the dataset, and that certification is reported as a fact rather than a judgement. It says nothing about behavior for an unknown or malformed code, which is the main remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause roughly earns its place given there is no output schema, and the lookup key and negative scope are front-loaded. However, the body is one sprawling semicolon-chained sentence enumerating a dozen facets, which makes it harder to scan than a short structured list would be.

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 correctly takes on the burden of describing what comes back and does so comprehensively, including explicit non-returns. For a read-only single-entity lookup this is close to complete; only error behavior for a missing code is unaddressed.

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 adds genuinely new semantics: the code accepts 'LC0564', lowercase 'lc0564' and even a bare '564', which is normalization behavior the schema's 'Catalogue code, e.g. LC0564 or LC0406-1' does not convey. It restates the eight available languages and en default, which the schema already implies, adding little there.

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?

The description states a precise verb and resource — retrieve everything the public dataset holds about a single composition, looked up by its code — and immediately enumerates the returned facets (names, family/type, texts, pages, media, certification, configurator status, exports). It also explicitly carves out ceramic compositions and points to ceramic_collection, so an agent can tell this apart from a generic search 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 Guidelines4/5

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

It gives a clear usage context (single-composition lookup by code) and an alternative route for ceramic-collection items via ceramic_collection. It also states negative scope — no price, no dimensions — which prevents wasted calls. It does not explicitly say to use search_compositions when the code is unknown, which is the obvious sibling alternative left to inference.

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