Skip to main content
Glama

Organise the Mailbox

manage_mailbox
Destructive

Organise threads, labels, settings, forwarding and drafts, link or mark a received message, take an employer's quiz it invites, and manage held replies, drafted replies, sending accounts, a custom domain order and a domain the member already owns. Sending is send_email. Actions: organize, update_settings, create_label, rename_label, delete_label, set_forwarding, approve_applying_address, save_draft, delete_draft, attach_file, remove_attachment, cancel_send, discard_held_reply, dismiss_ai_reply, redraft_ai_reply, resume_ai_reply, link_message, mark_message, take_quiz, ai_reply_settings, sender_settings, disconnect_sender, cancel_domain_order, connect_own_domain, check_own_domain, disconnect_own_domain, retry_domain_setup. 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": "manage_mailbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoThe item's key as the matching list answered it.
actionYes
paramsNoFields for the action. Call with action "help" to list each action's fields.
draft_idNoA Mailbox draft's id (32 hex).
attachment_idNoA draft attachment's id from manage_mailbox attach_file.
connection_idNoA connected sender's id from get_mailbox connected_senders.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "organize",
      -  "update_settings",
      -  "create_label",
      -  "rename_label",
      -  "delete_label",
      -  "set_forwarding",
      -  "approve_applying_address",
      -  "save_draft",
      -  "delete_draft",
      -  "attach_file",
      -  "remove_attachment",
      -  "cancel_send",
      -  "discard_held_reply",
      -  "dismiss_ai_reply",
      -  "ai_reply_settings",
      -  "sender_settings",
      -  "disconnect_sender",
      -  "cancel_domain_order",
      -  "connect_own_domain",
      -  "check_own_domain",
      -  "disconnect_own_domain",
      -  "retry_domain_setup",
      -  "help"
      -]New value: +[
      +  "organize",
      +  "update_settings",
      +  "create_label",
      +  "rename_label",
      +  "delete_label",
      +  "set_forwarding",
      +  "approve_applying_address",
      +  "save_draft",
      +  "delete_draft",
      +  "attach_file",
      +  "remove_attachment",
      +  "cancel_send",
      +  "discard_held_reply",
      +  "dismiss_ai_reply",
      +  "redraft_ai_reply",
      +  "resume_ai_reply",
      +  "link_message",
      +  "mark_message",
      +  "take_quiz",
      +  "ai_reply_settings",
      +  "sender_settings",
      +  "disconnect_sender",
      +  "cancel_domain_order",
      +  "connect_own_domain",
      +  "check_own_domain",
      +  "disconnect_own_domain",
      +  "retry_domain_setup",
      +  "help"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "organize",
      -  "update_settings",
      -  "create_label",
      -  "rename_label",
      -  "delete_label",
      -  "set_forwarding",
      -  "approve_applying_address",
      -  "save_draft",
      -  "delete_draft",
      -  "attach_file",
      -  "remove_attachment",
      -  "cancel_send",
      -  "discard_held_reply",
      -  "dismiss_ai_reply",
      -  "ai_reply_settings",
      -  "sender_settings",
      -  "disconnect_sender",
      -  "cancel_domain_order",
      -  "help"
      -]New value: +[
      +  "organize",
      +  "update_settings",
      +  "create_label",
      +  "rename_label",
      +  "delete_label",
      +  "set_forwarding",
      +  "approve_applying_address",
      +  "save_draft",
      +  "delete_draft",
      +  "attach_file",
      +  "remove_attachment",
      +  "cancel_send",
      +  "discard_held_reply",
      +  "dismiss_ai_reply",
      +  "ai_reply_settings",
      +  "sender_settings",
      +  "disconnect_sender",
      +  "cancel_domain_order",
      +  "connect_own_domain",
      +  "check_own_domain",
      +  "disconnect_own_domain",
      +  "retry_domain_setup",
      +  "help"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "organize",
      -  "update_settings",
      -  "create_label",
      -  "rename_label",
      -  "delete_label",
      -  "set_forwarding",
      -  "approve_applying_address",
      -  "save_draft",
      -  "delete_draft",
      -  "attach_file",
      -  "remove_attachment",
      -  "cancel_send",
      -  "discard_held_reply",
      -  "dismiss_ai_reply",
      -  "ai_reply_settings",
      -  "sender_settings",
      -  "disconnect_sender",
      -  "connect_sender_link",
      -  "domain_suggestions",
      -  "check_domain",
      -  "cancel_domain_order",
      -  "help"
      -]New value: +[
      +  "organize",
      +  "update_settings",
      +  "create_label",
      +  "rename_label",
      +  "delete_label",
      +  "set_forwarding",
      +  "approve_applying_address",
      +  "save_draft",
      +  "delete_draft",
      +  "attach_file",
      +  "remove_attachment",
      +  "cancel_send",
      +  "discard_held_reply",
      +  "dismiss_ai_reply",
      +  "ai_reply_settings",
      +  "sender_settings",
      +  "disconnect_sender",
      +  "cancel_domain_order",
      +  "help"
      +]
  4. Added

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the safety profile is known. The description adds value by revealing hidden side effects an agent would not guess from a name like 'organize' — it can take an employer's quiz, cancel a domain order, or disconnect a sender — but it never says which actions are irreversible (delete_label, delete_draft, cancel_send) or what permissions are required, so it misses the behavioural context the annotations cannot carry.

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

Conciseness2/5

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

The first sentence is an unstructured run-on that bundles unrelated capabilities, and the subsequent action enumeration duplicates the schema's action enum verbatim, wasting a long stretch of text. The one high-value instruction (use action 'help' for fields) is buried at the end rather than front-loaded.

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 28-action mega-tool with a free-form nested params object and no output schema, the definition is barely adequate: it delegates field-level detail to a runtime 'help' call, which is a reasonable escape hatch, but it does not describe the response shape, ordering constraints between domain/domain-order actions, or which actions need key vs draft_id vs connection_id.

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 coverage is 83% and the action enum already lists every value, including 'help'. The description's main contribution is telling the agent the params object is discovered via action 'help', which is genuinely useful. But its own action list merely repeats the enum rather than clarifying when each field is required or what key/draft_id/connection_id each action expects.

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 (mailbox) and enumerates 27 concrete actions, so an agent can see this is the catch-all mailbox mutation tool, and it explicitly excludes sending by routing that to send_email. However, the opening sentence is a sprawling run-on that mixes threads, labels, forwarding, drafts, quizzes, and domain orders without stating an organising principle, so the overall 'what does this tool do' answer is a list rather than a clear purpose.

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 useful routing cue ('Sending is send_email') and a discovery instruction ('Call with action "help" for each action's fields'), which helps the agent learn per-action parameters. But it never says when to use this versus get_mailbox for reads, nor which actions are prerequisites for others (e.g. a domain order before connect_own_domain), leaving the main when-to-use question implied.

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.