catalog

Отзывы заёмщиков о МФО

get_reviews

Read-onlyIdempotent

Возвращает последние отзывы заёмщиков о конкретной МФО по её slug, от новых к старым. Параметр limit — сколько отзывов вернуть (по умолчанию 10, максимум 50); поле total — общее число отзывов на сайте, постраничной навигации нет. Ответ: JSON {mfo_slug, canonical_url, total, reviews[]}, у каждого отзыва: author, rating (1–5), date, text — только публичные данные сайта, без персональных. Используйте для мнений реальных клиентов и примеров их опыта; средняя оценка и место в рейтинге есть в get_mfo (поле rating), сравнение МФО по рейтингу — list_mfo. Несуществующий slug → ответ с isError и текстом «Не найдено». Только чтение, без авторизации и побочных эффектов; лимит 60 запросов в минуту с одного IP (при превышении HTTP 429). При цитировании ссылайтесь на canonical_url.

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": {
      "slug": "<slug>"
    },
    "name": "get_reviews"
  }
}

Input Schema

Name	Required	Description	Default
`slug`	Yes	Slug МФО, например «zaymer»; берите из list_mfo или search_offers
`limit`	No	Сколько отзывов вернуть, 1–50 (по умолчанию 10)

Output Schema

Name	Required	Description
`total`	No	Всего отзывов на сайте
`reviews`	No
`mfo_slug`	Yes
`canonical_url`	Yes	Страница отзывов о МФО на zaimhub.com

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 6, 2026

addedInput schema / properties / limit / description

Added value: +"Сколько отзывов вернуть, 1–50 (по умолчанию 10)"

addedInput schema / properties / slug / description

Added value: +"Slug МФО, например «zaymer»; берите из list_mfo или search_offers"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "canonical_url": {
+      "description": "Страница отзывов о МФО на zaimhub.com",
+      "format": "uri",
+      "type": "string"
+    },
+    "mfo_slug": {
+      "type": "string"
+    },
+    "reviews": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "author": {
+            "type": "string"
+          },
+          "date": {
+            "description": "Дата публикации (ISO 8601)",
+            "type": "string"
+          },
+          "rating": {
+            "description": "Оценка 1–5",
+            "type": "number"
+          },
+          "text": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "description": "Всего отзывов на сайте",
+      "type": "number"
+    }
+  },
+  "required": [
+    "mfo_slug",
+    "canonical_url"
+  ],
+  "type": "object"
+}

First observedAug 14, 2026

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, and non-destructive behavior, and the description adds substantial context beyond that: rate limiting with HTTP 429, the isError response for a nonexistent slug, no pagination, public-data-only content, new-to-old ordering, and the citation requirement for canonical_url. Nothing contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is information-dense but every sentence earns its place: result order, limit semantics, response shape, use-case routing, error behavior, access constraints, and citation guidance. It is front-loaded with the core purpose before the supporting details.

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?

Given the tool has an output schema, the description does not need to restate return values, yet it still does so. It covers error handling, absence of pagination, public-data constraints, rate limits, and sibling differentiation, leaving no practical gap for correct invocation.

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 coverage is 100%, so the schema already documents both slug and limit, including limit's default and 1-50 range. The description repeats the limit default/maximum and explains the total field, but it adds no new parameter-level meaning that an agent could not already read from 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 opens with a precise verb-resource pair: it returns the latest borrower reviews for a specific MFO by slug, ordered newest to oldest. It also distinguishes itself by naming get_mfo for average rating and list_mfo for rating comparison, so an agent can tell it apart from siblings.

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?

It explicitly states when to use the tool: for real client opinions and examples of their experience. It also provides alternatives and exclusions: get_mfo gives the average rating and place in rating, while list_mfo handles rating comparison, so an agent knows which sibling to route to.

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

All catalog tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.