Skip to main content
Glama

Send email

send_email
Destructive

Send email from the member's Applystead Mailbox: drafts, replies, held replies, drafted replies, outreach and campaigns, and turn automatic replies on or off. Actions: send_draft, reply, confirm_held_reply, send_ai_reply, schedule_interview, full_auto_replies, send_outreach, send_campaign. 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": "send_email"
  }
}

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).
campaign_idNoA campaign's id from get_outreach campaigns (campaigns[].id).
outreach_idNoAn outreach message or thread id from get_outreach.
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. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "send_draft",
      -  "reply",
      -  "confirm_held_reply",
      -  "send_ai_reply",
      -  "full_auto_replies",
      -  "send_outreach",
      -  "send_campaign",
      -  "help"
      -]New value: +[
      +  "send_draft",
      +  "reply",
      +  "confirm_held_reply",
      +  "send_ai_reply",
      +  "schedule_interview",
      +  "full_auto_replies",
      +  "send_outreach",
      +  "send_campaign",
      +  "help"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "send_draft",
      -  "reply",
      -  "confirm_held_reply",
      -  "send_ai_reply",
      -  "full_auto_replies",
      -  "send_outreach",
      -  "help"
      -]New value: +[
      +  "send_draft",
      +  "reply",
      +  "confirm_held_reply",
      +  "send_ai_reply",
      +  "full_auto_replies",
      +  "send_outreach",
      +  "send_campaign",
      +  "help"
      +]
    • addedInput schema / properties / campaign_id
      Added value: +{
      +  "description": "A campaign's id from get_outreach campaigns (campaigns[].id).",
      +  "pattern": "^[a-f0-9]{32}$",
      +  "type": "string"
      +}
  3. Changed2 schema fields changed
    • changedInput schema / properties / mail_message_id / description
      Previous value: -"A received message's id: a calendar event's mailMessageId, or a Mailbox message id (i-…) without its leading \"i-\"."New value: +"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."
    • changedInput schema / properties / outreach_id / description
      Previous value: -"An outreach message or thread id from outreach."New value: +"An outreach message or thread id from get_outreach."
  4. Added

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds real context beyond that by revealing that a send-email tool also toggles automatic replies (full_auto_replies) and handles scheduled interviews, but it never warns that dispatched emails are irreversible or that campaign/outreach sends may reach external recipients at scale.

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?

The lead sentence is front-loaded and useful, and the 'help' pointer earns its place. However, the middle sentence restates all eight enum values already present verbatim in the action schema, which is pure duplication and consumes roughly half the description.

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 destructive, non-idempotent, open-world mutation tool with a nested opaque params object and no output schema, the description covers the action surface and the discovery mechanism but omits what a successful send returns, whether sends are queued vs immediate, and any confirmation/permission expectations. Adequate but missing behavior an agent should know before firing off emails.

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 86% for the flat fields, but the critical 'params' object is additionalProperties=true with no documented shape. The description compensates well by telling the agent to call action "help" to enumerate each action's required fields, which is meaningful guidance the schema cannot convey. It doesn't hint at what params each of the eight actions needs, but the discovery path is clear.

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

Purpose4/5

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

Names a specific verb (send) and resource (email from the member's Applystead Mailbox) and enumerates the concrete action families it covers: drafts, replies, held replies, outreach, campaigns, auto-replies. It does not explicitly distinguish itself from the manage_mailbox/manage_outreach siblings, but the 'send' framing vs 'manage' is reasonably legible.

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?

The only usage guidance is procedural – 'Call with action "help" for each action's fields' – which is useful for invocation but says nothing about when to reach for this tool versus manage_mailbox, manage_outreach, or get_mailbox. The per-action names imply their own use cases, but selection criteria are left to inference.

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.