Nextmail

Set out of office

setOutOfOffice

Destructive

Save the out of office reply of one address, or of a catch-all with *@domain, replacing what was saved. While it is active, each person who writes to the address gets the message once for the whole away period, as a reply in the same thread. Spam, newsletters and other bulk mail, automatic mail, bounces, blocked senders and the workspace's own addresses get no reply. startsAt and endsAt are ISO 8601 times: leave startsAt out to start now, or to keep the start of a reply that is already on, and endsAt out to keep it on until it is switched off. A new startsAt begins a new away period, in which everyone is answered once more. An empty subject answers with Re: and the subject received. contactsOnly answers only contacts and people the workspace has written to. enabled false keeps the text and stops the replies. getCurrentDate gives the time now.

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": {
      "address": "<address>",
      "message": "<message>"
    },
    "name": "setOutOfOffice"
  }
}

Input Schema

Name	Required	Description
`endsAt`	No
`address`	Yes	One address, such as hello@example.com, or *@example.com for the catch-all of a domain.
`enabled`	No
`message`	Yes
`subject`	No
`startsAt`	No
`contactsOnly`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing the replace-overwrite behavior, once-per-away-period reply semantics, threaded reply delivery, the full exemption list (spam, bulk, automatic mail, bounces, blocked senders, own addresses), and the empty-subject 'Re:' fallback. It also explains the stateful interaction between startsAt and a new away period.

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?

Front-loads the core action, then layers behavior and per-parameter guidance; nearly every sentence carries unique information. It reads as a dense run-on block without visual separation between behavior and parameter semantics, which slightly hurts scanability.

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, stateful mutation with no annotations beyond safety hints and no output schema, the description covers the write semantics, timing behavior, and per-parameter effects thoroughly. It does not mention what is returned or any permission/ownership requirements, which is a minor remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 14% schema description coverage across 7 parameters, the description compensates by giving meaning to nearly all of them: address (single vs catch-all form), startsAt/endsAt (ISO 8601, omission semantics, restarting the away period), enabled (keeps text but stops replies), contactsOnly (audience restriction), and subject (empty value produces 'Re:').

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?

States a specific verb ('Save') and resource ('the out of office reply'), plus the exact scope ('of one address, or of a catch-all with *@domain, replacing what was saved'). An agent can distinguish this from getOutOfOffice and clearOutOfOffice without opening either 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?

Gives concrete conditional guidance for the optional parameters: omit startsAt to start now, omit endsAt to keep it on indefinitely, set enabled=false to retain text but stop replies, contactsOnly to limit recipients. It stops short of naming sibling alternatives (clearOutOfOffice, getOutOfOffice) for stopping or reading the reply, which would have made routing fully explicit.

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

All Nextmail tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.