Skip to main content
Glama

Журнал действий аккаунта

get_workspace_activity
Read-onlyIdempotent

Возвращает журнал действий аккаунта, новые записи сверху: кто и когда создавал, публиковал, менял, переносил и удалял опросы, выгружал, удалял и открывал по ссылке ответы, приглашал и удалял участников, менял роли и доступ к папкам, а также кому отказали по правам роли. Каждая запись: action (код события, например quiz.published, answers.deleted, access.denied), source (cabinet — кабинет; api; wordpress — плагин WordPress; mcp — внешний ассистент; assistant — ассистент в кабинете и ИИ-генерация опроса), actor (кто, is_member — состоит ли сейчас в аккаунте), target (опрос, участник, роль или папка, exists — есть ли сейчас) и meta (подробности: число правок, формат выгрузки, число ответов, роль «было/стало», право и роль при отказе). Ответов респондентов в журнале нет. Только чтение; нужен тариф с журналом активности и право «Смотреть активность участников».

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": {
      "workspace_id": "<workspace_id>"
    },
    "name": "get_workspace_activity"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoПо какой день, YYYY-MM-DD, включительно, во времени аккаунта.
fromNoС какого дня, YYYY-MM-DD, включительно, во времени аккаунта.
pageNoНомер страницы с 1, по умолчанию 1.
groupNoГруппа действий: quizzes — опросы, answers — ответы, members — участники и роли, exports — выгрузки, deletions — удаления, denied — отказы в доступе.
quiz_idNoТолько события этого опроса.
user_idNoТолько действия этого пользователя (user_id из get_workspace_members).
per_pageNoЗаписей на странице: 20 (по умолчанию), 50 или 100.
workspace_idYesID воркспейса (из workspace://list).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description earns credit for the extra behavior it adds: ordering (newest first), the exact shape of each record (action with example codes, source enumerating cabinet/api/wordpress/mcp/assistant, actor with is_member, target with exists, meta payload contents), and the explicit exclusion of respondent answers. The tariff/permission gate is access behavior that annotations cannot express.

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 payload is front-loaded — scope and ordering come first, then record structure, then access requirements — and nearly every clause carries information the agent needs. The single very long sentence enumerating action types is dense but justified given the absence of an output schema; a bulleted split would read slightly better.

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 8 parameters, no output schema, and a read-only log, the description covers all the missing pieces: what a record looks like field by field, the ordering and pagination context, what data is deliberately absent, and the tariff/permission prerequisites. An agent has everything needed to decide to call it and to interpret the result.

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% and required/optional, enums (group, per_page) and date formats are all documented in the schema itself, so the baseline of 3 applies. The description mentions the action groups only indirectly through its event list and adds no filtering syntax or interaction rules between from/to, group and page beyond what the schema already says.

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 specific verb and resource ('Возвращает журнал действий аккаунта, новые записи сверху') and then enumerates the exact event classes captured (создание/публикация/изменение опросов, выгрузки и удаления ответов, участники и роли, отказы по правам). That enumeration is what separates it from log-like siblings such as get_integration_logs, get_quiz_email_log or get_booking_journal, which an agent can rule out without opening a schema.

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?

It states the concrete preconditions for use: a tariff that includes the activity journal and the 'Смотреть активность участников' permission, and it warns 'Ответов респондентов в журнале нет', which tells the agent when to reach for get_quiz_answers instead. It never names a sibling alternative or an explicit when-not condition, so it stops short of a 5.

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