Skip to main content
Glama

Artil — Email, SMS & Messaging for AI Agents

Send a message

messages.send
Destructive

Send a message from the agent account. To answer one, give its id in replyTo: the answer goes back the way it came. To start a conversation, give a channel and recipients in to. To pass a message on, give its id in forward and recipients in to; its files go along. Files to send go in attachments.

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": {
      "text": "<text>"
    },
    "name": "messages.send"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoWho gets a copy, addressed as in to; only email copies. To answer everyone, copy the others the message named in to and cc
toNoWho to send to: email takes email addresses; sms takes a phone number that texted the agent first, or another agent's number in the workspace; telegram takes the id of someone who wrote to the agent's bot first, the id of a group that tagged the bot, where everyone in the group reads the message, or a bot's @username; slack takes a person's email or member id, or a #channel the agent's bot is in, where everyone in the channel reads the message; url takes the id of one agent from team.list
textYesThe message, in plain text
agentNoThe id of the agent account to act as, from status. Leave it out when these tools act as one agent account.
channelNoThe channel to start a conversation on; a forward goes on its message's unless given
forwardNoThe id of a message to forward to the recipients in to: its sender, date, subject and text go below yours
replyToNoThe id of the message to answer; the answer goes to its sender, or to everyone the agent's own message went to. Answer another agent only if its message asks for an answer.
subjectNoThe subject, on a channel that has one; a new conversation there needs one, and an answer keeps its message's
attachmentsNoFiles to send: a file from a message the agent received or sent, by the id in its attachments, or a small text file by name, type and text. A file from this conversation cannot be sent; have it mailed to the agent, then send it on by its id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / channel / enum
      Previous value: -[
      -  "email",
      -  "sms",
      -  "telegram",
      -  "url"
      -]New value: +[
      +  "email",
      +  "sms",
      +  "telegram",
      +  "slack",
      +  "url"
      +]
    • changedInput schema / properties / to / description
      Previous value: -"Who to send to: email takes email addresses; sms takes a phone number that texted the agent first, or another agent's number in the workspace; telegram takes the id of someone who wrote to the agent's bot first, the id of a group that tagged the bot, where everyone in the group reads the message, or a bot's @username; url takes the id of one agent from team.list"New value: +"Who to send to: email takes email addresses; sms takes a phone number that texted the agent first, or another agent's number in the workspace; telegram takes the id of someone who wrote to the agent's bot first, the id of a group that tagged the bot, where everyone in the group reads the message, or a bot's @username; slack takes a person's email or member id, or a #channel the agent's bot is in, where everyone in the channel reads the message; url takes the id of one agent from team.list"
  2. Changed1 schema field changed
    • changedInput schema / properties / to / description
      Previous value: -"Who to send to: email takes email addresses; sms takes a phone number that texted the agent first, or another agent's number in the workspace; telegram takes the id of someone who wrote to the agent's bot first, or a bot's @username; url takes the id of one agent from team.list"New value: +"Who to send to: email takes email addresses; sms takes a phone number that texted the agent first, or another agent's number in the workspace; telegram takes the id of someone who wrote to the agent's bot first, the id of a group that tagged the bot, where everyone in the group reads the message, or a bot's @username; url takes the id of one agent from team.list"
  3. Changed2 schema fields changed
    • removedInput schema / properties / agent / format
      Removed value: -"uuid"
    • removedInput schema / properties / agent / pattern
      Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  4. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is known. The description adds the useful routing fact that a reply "goes back the way it came" and that a forward carries its files along, but it never explains why the call is flagged destructive (external, irreversible delivery) or what happens on partial failure. With annotations carrying the risk profile, this is adequate but thin.

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

Conciseness4/5

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

Four short sentences, one per mode, with the core purpose front-loaded and no filler. The clipped phrasing ("give its id in replyTo") costs a little readability but every sentence carries routing information.

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 9-parameter, multi-channel mutation tool with no output schema, the description covers the three send modes but leaves the agent without any statement of what comes back (message id, status) or channel-specific preconditions. Much of that gap is filled by the unusually detailed schema, so the description is workable but not complete on its own.

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 100%, so the baseline is 3. The description mostly restates what the schema already documents for replyTo, forward, to and attachments; the only genuine addition is that a forwarded message's files go along too. It says nothing about channel, subject, cc or agent, which the schema handles.

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 opening sentence states a specific verb and resource ("Send a message from the agent account") and the rest of the description enumerates the three distinct send modes: reply (replyTo), new conversation (channel + to), and forward (forward + to). It is clearly distinguishable from the read-only siblings messages.list and messages.read.

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 gives explicit mode-selection rules: use replyTo to answer, channel+to to start a conversation, forward+to to pass a message on. This is strong routing guidance. It stops short of any exclusion or precondition (e.g. when not to use it, or channel-specific limits), so it does not quite reach the top of the scale.

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.

Resources