Skip to main content
Glama

Закрыть или вернуть доступ участнику

set_workspace_member_blocked
Destructive

Закрывает участнику доступ к аккаунту, не удаляя его, или возвращает доступ. Пока доступ закрыт, участник не работает в этом аккаунте (кабинет, API, MCP), его ключ участника не действует; роль, папки, заметка и настройки API сохраняются, место в тарифе он не занимает: вернуть доступ можно, только если есть свободное место (иначе ошибка «нет свободного места»). Нельзя закрыть доступ владельцу, себе и тому, кто ещё не принял приглашение. Повтор того же состояния — успех без изменений. Нужно право «Участники».

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>",
      "member_id": "<member_id>",
      "blocked": "<blocked>"
    },
    "name": "set_workspace_member_blocked"
  }
}

Input Schema

NameRequiredDescriptionDefault
blockedYestrue — закрыть доступ, false — вернуть.
member_idYesID участника (member_id из get_workspace_members).
workspace_idYesID воркспейса (из workspace://list).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior2/5

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

The disclosure is substantively rich – it explains what still works for the blocked member (cabinet/API/MCP disabled, member key invalid), what is preserved (role, folders, note, API settings), seat accounting, and the free-seat error. However, 'Повтор того же состояния — успех без изменений' directly asserts idempotent no-op-on-repeat behavior, which contradicts the idempotentHint=false annotation and could mislead an agent about retry semantics.

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?

It is front-loaded – the block/restore purpose is in the first clause – and every sentence carries operational content (effects, preserved state, seat rule, restrictions, permission). The sentences are long and comma-chained with colons, which slightly taxes parsing, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, three-parameter mutation tool with no output schema, the description covers the effects, what is destroyed vs. preserved, error conditions, authorization requirements, and target restrictions – nearly everything an agent needs. Only the idempotency statement undercuts completeness by conflicting with the annotation.

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 all three parameters are documented in the schema, including that blocked=true closes and false restores. The description reinforces the dual-mode meaning and the eligibility constraints on member_id (owner/self/pending invitees are invalid targets), but adds no format or sourcing detail beyond what the schema already carries. Baseline 3 applies.

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 states a precise verb pair and resource: block a member's access to the account without deleting them, or restore it. It explicitly contrasts with deletion ('не удаляя его'), so an agent can distinguish it from remove_workspace_member without opening either schema, and it covers both directions of the same tool call.

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 gives explicit when-to-use conditions: close vs. restore access via the blocked flag, the prerequisite of a free seat for restoration (with the exact error), the prohibition on targeting the owner/self/pending invitees, and the required 'Участники' permission. Alternatives (deletion) are named and excluded.

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