Skip to main content
Glama

Search Vargov®Design compositions

search_compositions
Read-onlyIdempotent

Search 605 made-to-order lighting and decorative compositions by code, text, family, material, awards, or configurator availability, returning compact catalogue rows for detail lookup.

Instructions

Search the Vargov®Design catalogue: 605 made-to-order light and decorative compositions, codes LC0001…LC0602. Full-text over codes, type labels and the brand's own texts (description, where it works, style) in Russian and English; other site languages are matched too. Filters: family (lighting | decorative | sculptural-decor | floor-table-lamps); lit (true = the lighting family or a type label mentioning light/lamp/backlit — a hint derived from labels, not a measured property); awarded (has a listed award); configurable (opens in the 3D configurator with a full calculation: IFC4, FBX, PDF specification, tender sheet — 360 of 605); material: "ceramic" — the ceramic collection published at vargov.ru/en/ceramics (ceramic elements, ceramic with glass or crystal, ceramic or opaque white glass to choose; from the brand's own material marking). Returns compact rows: code, names RU/EN, family, type, flags, site pages, cover image, English snippet. Then use get_composition for details and build_configurator_link to open the configurator with the room plan. No prices or composition dimensions are published.

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_compositions"
  }
}

Input Schema

NameRequiredDescriptionDefault
litNotrue: light-emitting (hint from labels); false: decorative/unlit
limitNodefault 10, max 50
queryNoWords or a code, e.g. "hotel lobby", "birds", "гостиная", "LC0564"
familyNo
awardedNo
materialNo"ceramic": only the ceramic collection (vargov.ru/en/ceramics)
configurableNotrue: opens in the configurator with a full calculation (IFC4/FBX/PDF/tender sheet)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, closed-world, but the description adds substantive behavior beyond them: full-text coverage spans Russian and English with other site languages matched, and specifically warns that "lit" is "a hint derived from labels, not a measured property" — an unusually honest caveat. It also discloses coverage limits ("360 of 605" configurable) and states "No prices or composition dimensions are published," preventing futile follow-up queries.

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?

The one-paragraph form is front-loaded with the core purpose and the return-row summary, and nearly every clause carries information an agent needs. The dense parentheticals around material and configurable make it harder to scan than a short bulleted structure would be, keeping it below a 5 despite zero filler.

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 fully carries the return contract by enumerating the compact row fields (code, names RU/EN, family, type, flags, site pages, cover image, English snippet). For a 7-parameter search tool it covers scope, filter meaning, result shape, known limitations, and next steps — 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.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 71% schema coverage the schema already documents most parameters, yet the description still adds real meaning: awarded is glossed as "has a listed award," configurable as opening the 3D configurator with IFC4/FBX/PDF/tender-sheet outputs, and material ceramic as the specific collection at vargov.ru/en/ceramics with its sub-options and provenance. Only limit (default 10, max 50) is left entirely to the schema, which is sufficient.

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 ("Search the Vargov®Design catalogue") and immediately quantifies the corpus (605 made-to-order compositions, codes LC0001…LC0602). It states the searchable fields (codes, type labels, Russian/English brand texts) and what a result row contains, so an agent can distinguish this from get_composition without consulting 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?

Explicitly routes the agent forward: "Then use get_composition for details and build_configurator_link to open the configurator with the room plan," which is clear handoff guidance. Filter semantics (when to set lit, awarded, configurable, material) are spelled out. It lacks an explicit when-not-to-use statement for the other siblings (brand_facts, dealer_for_country, how_to_get_bim), leaving a small gap.

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