Skip to main content
Glama
Arsel MCP Server

Arsel MCP Server

Official
by Arsel-SA

Send SMS Campaign

send-sms-campaign
Destructive

Send an SMS campaign immediately or schedule it for a future time, delivering reviewed drafts to subscribed contacts in the campaign's lists, tags and segments.

Instructions

Send the SMS campaign now, or schedule it with scheduled_at. It goes to every subscribed contact in its lists, tags and segments. The campaign must be a draft or scheduled with every required field set. Call get-sms-campaign first and show the user its content. Tell the user the audience: if you set it in this conversation, name those lists, tags and segments and their sizes (get-list, get-segment). The campaign's own record doesn't include its audience, so otherwise ask the user to confirm it in the Arsel dashboard. Every recipient is billed for each part of the message, so tell the user how many parts it is (num_segments on the campaign). This reaches real people, and a message that has gone out cannot be recalled. Before calling it, show the user what will go out and to whom, and wait for their go-ahead. A scheduled, queued or sending campaign can be stopped with cancel-sms-campaign.

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": {
      "id": "<id>"
    },
    "name": "send-sms-campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe sms campaign id.
scheduled_atNoISO 8601 date-time in the future, with the user's UTC offset (e.g. 2026-12-01T09:00:00+03:00 for Saudi Arabia), to schedule the campaign. Omit to send now.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds substantial behavior beyond them — messages reach real people and cannot be recalled, every recipient is billed per message part, and cost depends on `num_segments`. It also discloses the important limitation that the campaign record does not include its audience, so the user must confirm it in the Arsel dashboard.

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?

Front-loaded with the action, then layered with constraints, cost, and safety in a logical order. Slight redundancy: the confirmation requirement appears once as 'show the user its content... tell the user the audience' and again as 'show the user what will go out and to whom, and wait for their go-ahead.' Reinforcing a destructive-action gate justifies most of that repetition.

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, billed, irreversible broadcast with only two parameters and no output schema, the description covers every decision-relevant fact: preconditions, audience verification, per-part billing, irreversibility, human confirmation, and the cancellation escape hatch. Nothing an agent needs in order to call it safely is missing.

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%, with both `id` and `scheduled_at` fully documented in the schema. The description only restates the send-now-versus-schedule behavior the schema already encodes; it adds no format, timezone, or state constraints beyond what is structured. Baseline 3 applies.

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 the SMS campaign) and immediately clarifies the two modes: send now or schedule via `scheduled_at`. The audience sentence ('every subscribed contact in its lists, tags and segments') makes clear this is a campaign-level broadcast, distinguishing it from a single-message `send-sms` send without naming it.

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?

Explicit preconditions: the campaign must be `draft` or `scheduled` with required fields set. It prescribes a workflow (call get-sms-campaign first, show content, name the audience, get user go-ahead) and names the alternative path for stopping an in-flight campaign via cancel-sms-campaign.

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

Deploy Server

Other Tools