Skip to main content
Glama

срезAI — Search API for AI agents

Answer Search — RAG с семантическим ранжированием

answer_search
Read-only

Полный RAG-цикл: поиск источников, семантическое ранжирование через BGE-reranker-v2-m3, чтение релевантных страниц и синтез финального ответа. Возвращает готовый ответ с указанием релевантности каждого источника (0–1).

Когда: нужен итоговый ответ на вопрос, а не список ссылок. Лучше web_search + read_url, когда требуется интерпретация и синтез по нескольким источникам. Конвейер: переформулировка запроса → параллельный поиск → BGE-reranker отбирает топ → чтение страниц → синтез ответа. Возвращает: текст ответа + sources (каждый с relevance, chars_read, read_success). Источники всегда отсортированы по убыванию relevance. Цена зависит от depth: fast — 3 кредита, balanced — 5 кредитов, deep — 10 кредитов.

Full RAG cycle: search, semantic reranking via BGE-reranker-v2-m3, page reading, answer synthesis. Returns a ready answer with relevance scores (0–1) for each source.

Use when: you need a final answer, not a list of links. Better than web_search + read_url when interpretation and synthesis across sources is required. Pipeline: query rewriting → parallel search → BGE-reranker picks top results → page reading → answer synthesis. Returns: answer text + sources (each with relevance, chars_read, read_success). Sources are always sorted by descending relevance. Cost depends on depth: fast — 3 credits, balanced — 5 credits, deep — 10 credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
depthNoГлубина: fast (2 страницы), balanced (5 страниц, по умолчанию), deep (10 страниц). Больше страниц — выше качество, дольше время. / Depth: fast (2 pages), balanced (5 pages, default), deep (10 pages). More pages = higher quality, longer time.balanced
queryYesВопрос или поисковый запрос / Question or search query
languageNoЯзык поиска и ответа / Search and answer language: auto, ru, enauto

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / depth / default
      Added value: +"balanced"
    • changedInput schema / properties / depth / description
      Previous value: -"Глубина поиска / Search depth: fast=2 pages, balanced=5, deep=10"New value: +"Глубина: fast (2 страницы), balanced (5 страниц, по умолчанию), deep (10 страниц). Больше страниц — выше качество, дольше время. / Depth: fast (2 pages), balanced (5 pages, default), deep (10 pages). More pages = higher quality, longer time."
    • addedInput schema / properties / language / default
      Added value: +"auto"
    • changedInput schema / properties / language / description
      Previous value: -"Язык поиска / Search language (default: auto)"New value: +"Язык поиска и ответа / Search and answer language: auto, ru, en"
    • changedInput schema / properties / query / description
      Previous value: -"Вопрос или задача / Question or search task"New value: +"Вопрос или поисковый запрос / Question or search query"
    • changedInput schema / properties / query / maxLength
      Previous value: -500New value: +2000
  2. Added
  3. Removed
  4. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive), the description discloses the internal pipeline stages, the return shape (answer text plus sources with relevance/chars_read/read_success), and a credit cost table tied to depth. The non-idempotent hint is consistent with the described reranking/synthesis variability, and the cost disclosure is information the annotations cannot carry.

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?

Content is well organized with labeled blocks (When / Pipeline / Returns / Cost) and the key differentiator is front-loaded. The main inefficiency is full duplication of every sentence in Russian and English, which roughly doubles the length for a single-language caller.

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?

Despite having no output schema, the description covers selection criteria, the full processing pipeline, the return structure, source ordering, and cost — everything needed to call the tool correctly and anticipate its output. No meaningful gap remains.

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 description coverage is 100%, so the schema already documents query, depth, and language, setting a baseline of 3. The description adds value beyond the schema by mapping each depth value to a concrete credit cost (fast 3, balanced 5, deep 10), which the schema's page-count descriptions do not provide.

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 compound verb pipeline (search, rerank, read, synthesize) and the concrete deliverable — a ready answer with per-source relevance scores. It explicitly distinguishes itself from the sibling combination web_search + read_url, so an agent can select it 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 Guidelines5/5

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

The 'When / Когда' block gives an explicit selection condition: use this when you need a final synthesized answer rather than a list of links. It names the alternative (web_search + read_url) and the exact condition (interpretation and synthesis across multiple sources) that favors this tool.

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