Skip to main content
Glama
ReftrixMCP
by TKMD

search.unified

Read-onlyIdempotent

Search layout sections, UI parts, motion patterns, backgrounds, and narratives in one semantic query, then merge parallel results by similarity score.

Instructions

Layout(セクション)・Part(UIコンポーネント)・Motion(アニメーション)・Background(背景デザイン)・Narrative(世界観)を横断的にセマンティック検索します。個別検索ツールを並列実行し、結果をsimilarityスコア順にマージして返却します。 / Cross-component semantic search across Layout sections, UI Parts, Motion patterns, Background designs, and Narratives. Executes individual search tools in parallel and merges results by similarity score.

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": {
      "query": "<query>"
    },
    "name": "search.unified"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoタグフィルター / Tags filter
limitNo取得件数(1-50、デフォルト: 10) / Result limit (1-50, default: 10)
queryYes検索クエリ(自然言語、1-500文字) / Search query (natural language, 1-500 chars)
typesNo検索対象タイプ(デフォルト: 全タイプ) / Target types (default: all types)
audienceNoターゲットオーディエンスフィルター / Target audience filter (e.g., 'Developer', 'Enterprise')
industryNo業種フィルター / Industry filter (e.g., 'SaaS', 'E-commerce')
webPageIdNoWebページIDでフィルター / Filter by web page ID
profile_idNo嗜好プロファイルID(検索結果のリランキングに使用) / Preference profile ID
query_typeNoクエリタイプ(auto: 自動分類、visual: 見た目、structural: レイアウト構造、functional: 機能、stylistic: スタイル) / Query type (auto: auto-classify)auto
facet_fieldsNoファセットフィールド指定(指定時はinclude_facetsが暗黙的にtrue)。未指定時は全4フィールド / Facet fields to compute (implicitly enables include_facets). Defaults to all 4 fields when omitted. sectionType: セクション/パーツタイプ, industry: 業種, audience: ターゲット, tags: タグ
include_facetsNoファセットカウント付与(デフォルト: false)。trueにすると sectionType/industry/audience/tags のカウントを返却 / Include facet counts (default: false). Returns counts for sectionType/industry/audience/tags when true
enable_rerankingNoCross-Encoderリランキング有効化(デフォルト: true) / Enable Cross-Encoder reranking (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.7.0
    • addedInput schema / properties / facet_fields / maxItems
      Added value: +4
    • addedInput schema / properties / types / maxItems
      Added value: +5
  2. Addedv0.3.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, closed-world), so the description's added value is the execution model: parallel sub-searches plus similarity-ordered merging, which tells the agent the results are aggregated rather than from a single index. It does not disclose failure handling if one sub-search fails, latency/cost expectations, or the shape of each merged result, keeping it below 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?

Two compact sentences that front-load the scope and then the mechanism; nothing is wasted. The Japanese/English duplication roughly doubles length, but that is a consistent localization pattern rather than padding, and each language version is tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 12 parameters and no output schema, the description carries some burden for describing what comes back, and it only says results are merged and sorted by similarity — it never mentions per-type fields, whether facet counts come back alongside hits, or what happens when `include_facets` is set. Adequate to select and invoke the tool, but thin on response expectations for a fairly rich search surface.

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 every one of the 12 parameters is already documented in the schema, including enums, defaults, and the implicit include_facets behavior. The description adds no parameter-level meaning (e.g., how `query_type` interacts with `enable_reranking`, or what `profile_id` reranking does), so the baseline 3 applies.

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 (cross-component semantic search) and enumerates the five resource domains it spans (Layout, Part, Motion, Background, Narrative). It also explains the mechanism — running the individual search tools in parallel and merging by similarity — which lets an agent distinguish it from siblings like layout.search, part.search, and motion.search without opening their schemas.

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?

The description makes clear this is the cross-cutting option that fans out to the individual search tools, implicitly contrasting with the single-domain siblings, and the `types` parameter signals it can also be narrowed. It stops short of an explicit 'use X instead when you only need one component type' rule or any guidance on when the extra cost of a parallel fan-out is warranted.

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