Skip to main content
Glama

Send a text message

send_message
Destructive

Sends a real iMessage/SMS from the owner's number to a phone number, email or existing chat: text, a file, or both. The file is either an attachment from a message (attachment_id, to forward it) or a new file you write (file).

Instructions

Sends a real iMessage/SMS from the owner's number to a phone number, email or existing chat: text, a file, or both. The file is either an attachment from a message (attachment_id, to forward it) or a new file you write (file). The server delivers only to recipients on its allowlist and enforces a length limit, file rules (files must be turned on; no programs or archives) and a rate limit; the result says whether the sent message was confirmed in history. Each call is a destructive action that the client asks the user to approve.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoRecipient as an E.164 phone number (+14155550123) or email. Give either `to` or `chat_id`.
fileNoA new file to send, up to 5 MB: its name and its content as text or base64. Needs files turned on (get_status: send.files).
textNoThe exact message text the user approved. Up to the server's max_chars (1,000 by default; see get_status). Optional when sending a file.
chat_idNoExisting chat id from list_chats (works for group chats). Give either `to` or `chat_id`.
attachment_idNoSend this attachment, for example to forward a photo: the "id" of an entry in a message's attachments list. Needs files turned on (get_status: send.files).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing delivery constraints the agent cannot otherwise know: recipient allowlist, length limit, file rules (files must be enabled, no programs or archives), rate limiting, the confirmation field in the result, and that the client asks the user to approve each call. This makes the destructive/openWorld annotations actionable rather than bare.

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?

Three front-loaded sentences: what it does, how the payload is composed, then the limits and approval behavior. Every clause carries information not available elsewhere; there is no filler or restatement of the name.

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, open-world mutation with five optional params and no output schema, the description covers approval, limits, and what the result reports. It stops short of describing failure modes (e.g., what happens on a non-allowlisted recipient or an unconfirmed send), which would fully close the loop.

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 baseline is 3, but the description adds the mutual-exclusivity relationship between file and attachment_id and clarifies that text is optional when a file is sent. It also ties files to the get_status send.files gate, which the schema mentions only in two of the params.

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 ('Sends a real iMessage/SMS from the owner's number') and enumerates the destination types and payload modes (text, file, or both). The read-only siblings listed (get_messages, list_chats, search_messages) are clearly distinguishable from this write tool.

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?

Explains the operative conditions for choosing a path: send to a phone number/email vs an existing chat, and that the file is either a forwarded attachment_id or a newly written file. It does not name an alternative tool, but no sibling send tool exists, so the missing piece is minimal.

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