Skip to main content
Glama

Своя почтовая служба

manage_workspace_smtp
Destructive

Своя почтовая служба аккаунта: письма респондентам уходят через SMTP владельца, а не сервиса. Инструмент показывает настройки (пароль не отдаётся — только признак, что он задан), включает и выключает уже заведённое подключение, отправляет пробное письмо на адрес владельца ключа и отдаёт журнал отправок с текстом отказа почтового сервера. Само подключение — хост, логин, пароль — заводит человек в кабинете: чужие учётные данные здесь не принимаются.

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>",
      "action": "<action>"
    },
    "name": "manage_workspace_smtp"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoСколько записей журнала вернуть, от 1 до 200. По умолчанию 50.
actionYesЧто сделать: show — настройки, logs — журнал отправок, enable — включить, disable — выключить, test — пробное письмо.
offsetNoСколько записей журнала пропустить.
workspace_idYesID workspace. Взять из workspace://list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=true, idempotent=false and openWorld=true; the description goes further by disclosing that the password is masked on read, that sending a test letter has an external side effect, and what the diagnostics contain. It does not spell out what disabling does to in-flight respondent mail or that credentials must pre-exist as a precondition beyond 'created in the dashboard', leaving modest room given the destructive hint.

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?

Three sentences, front-loaded with the purpose and the routing model, then the operation list, then the constraint. Dense and free of filler; the action enumeration is slightly chained but every clause carries distinct information.

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?

There is no output schema, and the description compensates by explaining what 'show' returns (settings minus the password), what 'logs' returns (entries with the server's rejection text), and where the test letter is sent. Combined with the setup precondition, an agent has enough to choose an action correctly; only the precise effect of disable on ongoing sending is left implicit.

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?

With schema coverage at 100% the baseline is 3, but the description adds meaning the schema does not: the password field is never returned, only a flag that it is set; the test letter goes to the key owner's address rather than an arbitrary recipient; and the log carries the mail server's refusal text. These clarify the action-dependent behavior of the enum beyond the one-line enum descriptions.

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 the resource (the account's own SMTP mail service) and then enumerates every operation the tool performs: showing settings, enabling/disabling an existing connection, sending a test letter to the key owner, and returning a send log with the mail server's refusal text. It also draws a hard scope boundary — connection credentials are created by a human in the dashboard, not here — which no sibling tool's name would imply.

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 clearly states when the tool applies (owner-mail routing, toggling an already-created connection, diagnostics via test letter and log) and an explicit exclusion (host/login/password cannot be supplied here; foreign credentials are rejected). It does not name an alternative tool for cases the agent might expect, but the siblings listed are unrelated workspace resources rather than substitutes.

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