Skip to main content
Glama
Sign In

Nextmail

by sh.nextmail
OverviewDiscussionsAdmin

Create calendar login

createCalendarLogin

Create a calendar sign-in, a username and password that sign calendar and contacts apps (Apple Calendar and Contacts, Thunderbird, DAVx5) in to a person's calendars, the calendars and address books shared with them, and their contacts, for someone with or without an email address. It never opens mail and never sends: mail apps refuse it. The password is shown this once, so hand it to the person straight away. Pass appleProfile to also get an Apple configuration profile that sets up an iPhone, iPad or Mac in one step. Both are secrets.

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": {
      "name": "<name>"
    },
    "name": "createCalendarLogin"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesWhat to call it, such as the device it is for.
memberNoThe member id of the person it is for, as listWorkspaceMembers gives it. Leave it out for your own. Another member needs the workspace owner or a role that manages members.
appleProfileNoAlso return the Apple configuration profile, the XML of a .mobileconfig file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the key behavioral traits: the credential secret is displayed only once, the returned values are secrets, mail protocols are refused so the login is scoped to calendar/contacts, and appleProfile changes the response shape. This is exactly the non-obvious behavior an agent needs for a credential-minting mutation.

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?

Purpose and scope are front-loaded in the first sentence, and each later sentence adds distinct information (mail exclusion, one-time secret, appleProfile, secret handling). The enumeration of calendars/shared address books/contacts is slightly wordy but not wasted.

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?

For a no-output-schema mutation that mints credentials, the description covers what is produced (username/password shown once, optional profile), how to handle it, and what the login cannot do. Permission requirements for the `member` parameter live in the schema, so nothing an agent needs to call this correctly 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; the description adds real meaning on top by explaining what appleProfile actually yields (an Apple configuration profile that sets up an iPhone, iPad or Mac in one step) and by labeling both outputs as secrets. It does not elaborate the `name` or `member` parameters, but those are already fully documented in the schema.

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?

A specific verb (Create) plus a precisely delimited resource (a calendar sign-in: username + password for calendar/contacts apps), including which clients it works with and what it does and does not reach (never opens mail, never sends). An agent can distinguish it from revokeCalendarLogin, listCalendarLogins and createCalendarLoginProfileLink without opening the 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 clearly when the tool applies — a person with or without an email address, needing app sign-in rather than mail — and the operational instruction to hand over the password immediately. It stops short of naming when-not-to-use or naming siblings as alternatives (e.g. the profile-link route), so it is clear context without explicit exclusions.

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

All Nextmail toolsInspect
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.

Resources