Skip to main content
Glama
TKMD
by TKMD

layout.search

Read-onlyIdempotent

Search section patterns semantically with natural language queries in English or Japanese. Filter by section type or use vision search for visual similarity.

Instructions

セクションパターンを自然言語クエリでセマンティック検索します。日本語・英語の両方に対応しています。hero、feature、cta、testimonial、pricing、footer等のセクションタイプでフィルタリングできます。use_vision_search=trueでvision_embeddingを使用したハイブリッド検索(RRF: 60% vision + 40% text)が可能です。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo取得件数(1-50、デフォルト: 10)
queryYes検索クエリ(日本語または英語、1-500文字)
offsetNoオフセット(0以上、デフォルト: 0)
filtersNo検索フィルター
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 (used for search result reranking)
includeHtmlNoHTMLスニペットを含めるか(デフォルト: false)- レガシー互換、include_html推奨
search_modeNo検索モード。text_only: text_embeddingのみを使用(デフォルト)。vision_only: vision_embeddingのみを使用。combined: 両方を使用してRRF統合検索。text_only
include_htmlNoHTMLスニペットを含めるか(デフォルト: false)- snake_case正式形式
include_previewNoサニタイズ済みHTMLプレビューを含めるか(デフォルト: true)
project_contextNoプロジェクトコンテキスト解析オプション。プロジェクトのデザインパターンを検出し、検索結果の適合度を評価します。
use_vision_searchNoVision検索を有効化。vision_embeddingを使用したセマンティック検索を行います(デフォルト: false)
multimodal_optionsNoマルチモーダルオプション。search_mode='combined'時のRRF統合パラメータ。
preview_max_lengthNoHTMLプレビューの最大文字数(100-1000、デフォルト: 500)
auto_detect_contextNoクエリから業界・スタイルコンテキストを自動推論し、結果をブーストします。推論されたコンテキスト(業界: technology/ecommerce/healthcare等、スタイル: minimal/bold/corporate等)にマッチする結果の類似度スコアが最大0.15ブーストされます(デフォルト: true)
vision_search_queryNoVision検索クエリ(use_vision_search=true時に使用)
vision_search_optionsNoVision検索オプション(use_vision_search=true時に使用)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed5 schema fields changedv0.3.0
    • addedInput schema / properties / filters / properties / audience
      Added value: +{
      +  "description": "ターゲットオーディエンス(例: b2b, b2c, enterprise) / Target audience filter",
      +  "maxLength": 100,
      +  "type": "string"
      +}
    • addedInput schema / properties / filters / properties / industry
      Added value: +{
      +  "description": "業種フィルター(例: tech, finance, healthcare) / Industry filter",
      +  "maxLength": 100,
      +  "type": "string"
      +}
    • addedInput schema / properties / filters / properties / tags
      Added value: +{
      +  "description": "タグフィルター / Tag filter",
      +  "items": {
      +    "maxLength": 50,
      +    "type": "string"
      +  },
      +  "maxItems": 10,
      +  "type": "array"
      +}
    • addedInput schema / properties / filters / properties / webPageId
      Added value: +{
      +  "description": "WebページIDでフィルター / Filter by web page ID",
      +  "format": "uuid",
      +  "type": "string"
      +}
    • addedInput schema / properties / filters / properties / webPageUrl
      Added value: +{
      +  "description": "WebページURLでフィルター / Filter by web page URL",
      +  "format": "uri",
      +  "type": "string"
      +}
  2. Addedv0.1.8

TDQS

A4/5.0
Behavior4/5

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

The description adds behavioral details beyond annotations, such as language support, filter options, and the hybrid search formula (60% vision + 40% text). It does not contradict the readOnly and idempotent hints.

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 description is concise (3 sentences) and front-loaded with the main purpose. It efficiently conveys key features but includes some technical detail (RRF percentages) that could be more accessible.

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?

Given the complexity of 16 parameters with nested objects, the description covers the main search and filter capabilities but does not explain the return value format or all advanced options (e.g., auto_detect_context, profile_id). It is moderately complete.

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 baseline is 3. The tool description adds a little extra context (e.g., vision search usage), but most parameter details are already in 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?

The description clearly states it searches section patterns via semantic natural language queries, lists supported section types, and mentions bilingual support. It distinguishes from sibling search tools (background.search, part.search) by specifying 'section patterns' and advanced vision search.

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 provides clear context for when to use the tool (semantic search of section patterns with filtering and optional vision search). However, it does not explicitly state when not to use it or compare with alternatives.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TKMD/ReftrixMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server