Skip to main content
Glama

Read the Mailbox

get_mailbox
Read-onlyIdempotent

The member's Mailbox: threads, messages, attachments, contacts, settings, drafts, held replies, drafted replies (and a reply drafted now), sending accounts and custom domain quotes. Actions: threads, thread, reply_address, messages, attachment, contacts, settings, applying_address, forwarding, draft, held_replies, held_reply, held_reply_attachment, ai_replies, draft_reply, connected_senders, connect_sender_link, domain_suggestions, check_domain. Call with action "help" for each action's fields.

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": "get_mailbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoThe item's key as the matching list answered it.
indexNoAn attachment's position (0 for the first).
actionYes
paramsNoFields for the action. Call with action "help" to list each action's fields.
draft_idNoA Mailbox draft's id (32 hex).
mail_message_idNoA received message's id: its Mailbox id (i-…) or the same id without "i-" (a calendar event's or RSVP draft's mailMessageId); either works.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "threads",
      -  "thread",
      -  "reply_address",
      -  "messages",
      -  "attachment",
      -  "contacts",
      -  "settings",
      -  "applying_address",
      -  "forwarding",
      -  "draft",
      -  "held_replies",
      -  "held_reply",
      -  "held_reply_attachment",
      -  "ai_replies",
      -  "connected_senders",
      -  "connect_sender_link",
      -  "domain_suggestions",
      -  "check_domain",
      -  "help"
      -]New value: +[
      +  "threads",
      +  "thread",
      +  "reply_address",
      +  "messages",
      +  "attachment",
      +  "contacts",
      +  "settings",
      +  "applying_address",
      +  "forwarding",
      +  "draft",
      +  "held_replies",
      +  "held_reply",
      +  "held_reply_attachment",
      +  "ai_replies",
      +  "draft_reply",
      +  "connected_senders",
      +  "connect_sender_link",
      +  "domain_suggestions",
      +  "check_domain",
      +  "help"
      +]
    • addedInput schema / properties / mail_message_id
      Added value: +{
      +  "description": "A received message's id: its Mailbox id (i-…) or the same id without \"i-\" (a calendar event's or RSVP draft's mailMessageId); either works.",
      +  "pattern": "^[A-Za-z0-9_-]{1,4096}$",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "threads",
      -  "thread",
      -  "reply_address",
      -  "messages",
      -  "attachment",
      -  "contacts",
      -  "settings",
      -  "applying_address",
      -  "forwarding",
      -  "draft",
      -  "held_replies",
      -  "held_reply",
      -  "held_reply_attachment",
      -  "ai_replies",
      -  "connected_senders",
      -  "help"
      -]New value: +[
      +  "threads",
      +  "thread",
      +  "reply_address",
      +  "messages",
      +  "attachment",
      +  "contacts",
      +  "settings",
      +  "applying_address",
      +  "forwarding",
      +  "draft",
      +  "held_replies",
      +  "held_reply",
      +  "held_reply_attachment",
      +  "ai_replies",
      +  "connected_senders",
      +  "connect_sender_link",
      +  "domain_suggestions",
      +  "check_domain",
      +  "help"
      +]
  3. Added

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds the action surface and the help escape hatch, but says nothing about pagination, result shape, or limits. It also lists `draft_reply` ("a reply drafted now") and `connect_sender_link` under a read-only tool without clarifying that these do not persist state, which leaves a small ambiguity an agent must resolve by trial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the resource and reads as a single dense sentence, with no filler prose. But the 19-action enumeration duplicates the schema enum verbatim and consumes most of the text, which by the scoring rules earns no credit; the only high-value clause is the final help instruction.

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

Completeness3/5

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

For a 6-parameter, 20-action dispatcher with a free-form nested `params` object and no output schema, the description does the minimum: it tells the agent how to discover per-action fields. It does not cover return shapes, which action requires which key/id, or how it relates to `manage_mailbox`, leaving real gaps for a tool of this complexity.

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 description coverage is 83%, so the schema already documents `key`, `index`, `draft_id` and `mail_message_id`. The one genuinely opaque parameter is `params`; the description's help pointer would matter there, but the same instruction is already present in the `params` schema description, so it adds little beyond structured data. The action list merely restates the enum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (the member's Mailbox) and enumerates the sub-resources it exposes, so an agent can see this is a read dispatcher over threads, messages, attachments, contacts, settings and drafts. However, it is a noun dump rather than a stated verb+scope, and it never distinguishes itself from the sibling `manage_mailbox`, which an agent will almost certainly weigh against it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is one concrete procedural hint: call with action "help" to discover each action's fields, which is genuinely useful for a dispatcher. But there is no when-to-use guidance, no statement that this is the read path versus `manage_mailbox` for mutations, and no prerequisites or exclusions.

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.