Skip to main content
Glama

срезAI — Search API for AI agents

by ru.srezai
OverviewDiscussionsAdmin

Проверить утверждение по источникам / Verify a claim against sources

verify_claim
Read-onlyIdempotent

Проверяет утверждение: ищет источники, читает несколько независимых страниц и возвращает вердикт с дословными цитатами. Каждая цитата сверена с текстом страницы — не найденная в тексте отбрасывается вместе со своим доводом.

Когда: факт, который нельзя брать на веру — цифра, дата, «X поддерживает Y», утверждение из ответа пользователя или из вашей же памяти. Особенно если ваш контекст не вмещает 4–5 страниц целиком: вся черновая работа делается на нашей стороне, к вам приходят только вердикт и цитаты. Когда не: нужен обзор темы — deep_research; нужен текст конкретной страницы — read_url. Вердикт: supported — источники подтверждают; refuted — опровергают; mixed — расходятся между собой; unverified — подтверждения не нашлось. Последние два — нормальный результат, а не ошибка: значит, утверждение нельзя считать проверенным. Считает в независимых доменах: три цитаты с одного сайта — один голос. Смотрите agreeing/disagreeing и confidence, а не только вердикт. Если сайт не открылся, слот не теряется: берём следующего кандидата из выдачи, поэтому прочитанных источников обычно ровно столько, сколько вы заказали. Когда проверка всё же вышла неполной, это сказано в вердикте и в caveats. Возвращает: вердикт, уверенность, цитаты со ссылками и оговорки. Источников — 2–5. Время: 15–60 с / 15–60 s. Цена: 8 кредитов (поиск, чтение источников и работа модели).

Verifies a statement: searches for sources, reads several independent pages and returns a verdict with verbatim quotes. Every quote is checked against the page text — one that is not found there is dropped along with its argument.

Use when: a fact you should not take on trust — a number, a date, "X supports Y", a claim from the user or from your own memory. Especially when your context cannot hold 4–5 pages at once: the legwork happens on our side, you receive only the verdict and the quotes. Do not use when: you need an overview of a topic — deep_research; you need the text of one specific page — read_url. Verdict: supported — the sources confirm it; refuted — they contradict it; mixed — they disagree with each other; unverified — no confirmation was found. The last two are normal outcomes, not errors: they mean the claim cannot be treated as verified. Counted in independent domains: three quotes from one site are one voice. Read agreeing/disagreeing and confidence, not just the verdict. If a site does not open, the slot is not lost: the next candidate from the search results is read instead, so you usually get exactly the number of sources you asked for. When the check still came out incomplete, the verdict and the caveats say so. Returns: verdict, confidence, quotes with links and caveats. Sources: 2–5. Time: 15–60 с / 15–60 s. Cost: 8 credits (search, source reading and model work).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
claimYesУтверждение одной фразой, как проверяемый факт: «Node.js 22 — LTS», «ставка НДС для IT-услуг в России 20%». Не вопрос и не тема: чем конкретнее формулировка, тем точнее проверка. / The statement as a single sentence, phrased as a checkable fact: "Node.js 22 is LTS". Not a question and not a topic: the more specific the wording, the sharper the check.
queryNoСвой поисковый запрос, если утверждение плохо ищется как есть (длинное, со сленгом). По умолчанию ищем по тексту утверждения. / A custom search query when the claim searches poorly as written (long, slangy). By default the claim text itself is the query.
languageNoЯзык поиска источников / Source search language: auto, ru, en
timeRangeNoСвежесть источников — для утверждений, которые могли устареть (цены, версии, должности): all, day, week, month, year. / Source recency — for claims that may have gone stale (prices, versions, job titles): all, day, week, month, year.
maxSourcesNoСколько независимых источников читать (2–5, по умолчанию 4). Меньше — быстрее, больше — надёжнее. На цену не влияет. / How many independent sources to read (2–5, default 4). Fewer is faster, more is sturdier. Does not affect the price.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / timeRange / description
      Previous value: -"Свежесть источников — для утверждений, которые могли устареть (цены, версии, должности): '', day, week, month, year. / Source recency — for claims that may have gone stale (prices, versions, job titles): '', day, week, month, year."New value: +"Свежесть источников — для утверждений, которые могли устареть (цены, версии, должности): all, day, week, month, year. / Source recency — for claims that may have gone stale (prices, versions, job titles): all, day, week, month, year."
  2. Changed1 schema field changed
    • changedInput schema / properties / timeRange / enum
      Previous value: -[
-  "",
-  "day",
-  "week",
-  "month",
-  "year"
-]New value: +[
+  "all",
+  "day",
+  "week",
+  "month",
+  "year"
+]
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, open-world, non-destructive, but the description adds substantial context beyond them: quote-against-page-text verification with dropped quotes, the four verdict values and their meaning, independent-domain counting, slot replacement when a site fails to open, incompleteness surfacing in caveats, source count, latency (15–60s) and cost (8 credits).

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 dense and well front-loaded with labeled blocks (verdict list, when/when-not, returns, time, cost), so scanning is easy. However, the entire text is duplicated in Russian and English, roughly doubling length without adding information for any single reader, which is the one structural inefficiency.

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 carries the full burden of explaining returns and does so: verdict, confidence, quotes with links, agreeing/disagreeing, and caveats, plus the semantics of mixed and unverified outcomes. Nothing an agent needs to interpret the result is missing.

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 parameter (claim, query, language, timeRange, maxSources) is already documented in the schema with enums and default values. The description only restates the 2–5 source range consistent with maxSources and adds cost/latency context; per the high-coverage baseline this is a 3.

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 and resource: it verifies a claim by searching sources, reading several independent pages, and returning a verdict with verbatim quotes. It explicitly distinguishes itself from siblings by naming deep_research and read_url as the tools for adjacent needs. An agent can tell what this does 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?

Has explicit 'Use when' (a fact that must not be taken on trust; context too small to hold 4–5 pages) and 'Do not use when' (topic overview → deep_research; single page text → read_url) sections. Sibling routing is unambiguous, which is exactly what is needed in a crowded toolset.

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

All срезAI — Search API for AI agents toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources