Skip to main content
Glama

send_email

Destructive

Compose and send a Proton Mail email after user approval, with HTML and plain-text body, CC/BCC, sender selection, and optional threaded replies.

Instructions

Send an email (HTML + plain-text alternative) from the user's Proton address. IRREVERSIBLE.

Only call this after showing the user the exact sender, recipients, subject and body and receiving their explicit approval in chat. from_address picks which of the user's addresses sends it (see list_sender_addresses). If omitted, new emails go out from the default address and replies from the address the original was sent to. The body is light Markdown, rendered to HTML: blank line = new paragraph, single newline = line break, lines starting with "- " = bullet list, "1. " = numbered list, bold, italic, text. Don't use headings, tables or raw HTML. Write the signature as the last paragraph. to/cc/bcc accept comma-separated addresses ("Name a@b.c, d@e.f"). To reply, pass reply_to_uid (and reply_folder) of the original email: the reply is threaded with it. Write the subject yourself (e.g. "Re: "). Replies quote the original message below the body, like Proton does ("On , wrote:" + quoted text); don't paste it into body yourself. Pass include_original=False to leave it out. A copy lands in the Sent folder automatically.

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_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNo
toYes
bccNo
bodyYes
subjectYes
from_addressNo
reply_folderNoINBOX
reply_to_uidNo
include_originalNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds substantially beyond them: the IRREVERSIBLE warning is front-loaded, the automatic Sent-folder copy is disclosed, and the reply-quoting behavior ('On <date>, <sender> wrote:' + quoted text, with include_original to suppress) is spelled out so the agent won't duplicate the original into the body.

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?

Front-loads the two facts that matter most (what it does, and that it is irreversible plus approval-gated), then proceeds in a scannable order: sender, body format, recipients, reply, side effects. Nearly every line carries operational constraints rather than filler.

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

Completeness4/5

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

For a destructive nine-parameter tool with no annotations-level detail and no output schema, this covers authorization, formatting, threading, and side effects comprehensively. The only gap is that it does not say what is returned on success (e.g. a message or thread identifier) that an agent might need for follow-up operations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the full burden and does: from_address semantics and its default resolution (default address for new mail, original recipient address for replies), comma-separated address syntax with display names for to/cc/bcc, reply_folder default context, include_original, and the Markdown subset accepted by body. That accounts for all nine parameters.

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?

States a specific verb and resource ('Send an email ... from the user's Proton address') plus the concrete output format (HTML + plain-text alternative). It is unmistakably distinct from every sibling, all of which are read/list operations.

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

Usage Guidelines5/5

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

Gives an explicit precondition ('Only call this after showing the user the exact sender, recipients, subject and body and receiving their explicit approval in chat') and routes to the sibling list_sender_addresses for address selection. It also distinguishes the reply path (pass reply_to_uid/reply_folder) from a fresh send, and when to set include_original=False.

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