Skip to main content
Glama

Входы в аккаунт

manage_user_sessions
Destructive

Активные входы в аккаунт: где человек ещё залогинен и закрытие лишнего входа. Показывает устройство, браузер, город и когда заходили последний раз. Внимание: close_all закрывает ВСЕ входы в браузерах, включая тот, из которого человек сейчас работает в кабинете, — в кабинете эта кнопка оставляет текущий вход, а здесь текущего входа нет, потому что ассистент работает по ключу. Поэтому close_all требует подтверждения.

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": {
      "action": "<action>"
    },
    "name": "manage_user_sessions"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesЧто сделать: list — список входов, close — закрыть один, close_all — закрыть все.
session_idNoИдентификатор входа из list. Нужен для close.
confirm_close_allNoПодтверждение для close_all: человека выкинет и из кабинета, в котором он сейчас работает.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, but the description goes well beyond that by spelling out exactly what is destroyed (all browser sessions, including the one the person is working from), why the cabinet's built-in protection is absent, and that a confirmation parameter is mandatory. This is precisely the extra context annotations cannot convey.

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 purpose is front-loaded in the first sentence and the destructive warning follows in the natural place. The close_all explanation restates the cabinet-vs-API contrast twice in slightly different words, which costs a little tightness but does not bury the key warning.

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 still covers what list returns and what the destructive action destroys, plus the confirmation requirement. For a three-parameter tool with one required enum, nothing an agent needs in order to call it safely is missing.

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 coverage is 100%, so the baseline is 3, and the description adds real meaning on top: it explains the semantic weight of confirm_close_all and why close_all has no implicit 'current session' exception. The link between session_id and the close action is only covered by the schema, not elaborated in the description.

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 names a concrete resource (active account sessions) and the specific operations performed on it: listing where the person is still logged in, closing one session, closing all. It also states what the listing shows (device, browser, city, last login), so an agent knows the tool's output shape from the description alone, and none of the sibling tools deal with sessions so there is no ambiguity to resolve.

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?

The description gives explicit guidance for the risky branch: close_all wipes every browser session and therefore requires confirmation, and it explains why the usual 'keep the current session' safeguard does not apply here because the assistant authenticates by key. It does not state the ordinary trigger conditions (e.g. use when the user asks about logins or suspects a compromise), leaving the plain list/close paths to the enum descriptions.

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