Skip to main content
Glama

send_mail

Destructive

Sends a plain-text email with optional attachments, choosing the sender account when needed and saving a draft unless confirmed.

Instructions

Send a plain text email, with files attached when 'attachments' is given. Without 'confirm' true nothing is sent: the message is saved as a draft. With more than one Mail account, 'from' must say which one sends. Ask the user when it is not clear. If Mail is not running, applesauce opens it hidden in the background and leaves it open. Sending cannot be undone. On Gmail accounts, Mail may leave a copy in Drafts.

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": {
      "to": "<to>",
      "subject": "<subject>",
      "body": "<body>"
    },
    "name": "send_mail"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCc addresses. Each must contain @.
toYesTo addresses. Each must contain @.
bccNoBcc addresses. Each must contain @.
bodyYesPlain text body.
fromNoSender: an account name, or one address of an account (from list_accounts).
confirmNoMust be true to send.
subjectYesSubject.
attachmentsNoAbsolute paths of files to attach. At most 10 files, 25 MB for each file and 25 MB in all. Folders, app bundles and files in secret folders (~/.ssh, ~/Library/Keychains and similar) are refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

The description adds substantial behavior beyond the annotations: confirm gating, draft fallback, irreversibility, opening Mail in the background when needed, and possible Gmail Drafts copies. These details align with the destructive annotation and give the agent the side-effect context it needs before calling the tool.

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

Conciseness5/5

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

The description is front-loaded with the primary action and then layers in the important guardrails and edge cases. Every sentence carries useful information, including the confirm behavior, account selection rule, background launch side effect, irreversibility, and Gmail Drafts caveat.

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 destructive send tool with no output schema, the description covers the critical operational context: confirmation, draft fallback, account ambiguity, app launch behavior, irreversibility, and Gmail-specific side effects. An agent has enough information to invoke it safely and correctly.

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 parameter definitions already carry most of the burden. The description still adds meaningful semantics for confirm, which changes the operation into a draft save, and for from, which must identify the sending account when multiple accounts exist.

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?

The description states a specific verb and resource: send a plain text email, optionally with attached files. It also explains the confirm-gated send-versus-draft behavior, which helps distinguish it from draft-related siblings even without naming them.

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?

The description clearly explains the key usage condition: confirm must be true to send, otherwise the message becomes a draft. It also gives guidance for multiple Mail accounts and tells the agent to ask the user when unclear, though it does not explicitly name alternative tools such as send_draft or create_draft.

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