Skip to main content
Glama

mu

by mu.micro
OverviewDiscussionsAdmin

Send sms

sms_send
Destructive

Message somebody from this instance's number, by text or on WhatsApp. A text is charged per 160-character segment; WhatsApp is charged per 24-hour conversation and only reaches somebody who wrote in within the last day. Capped per day either way, and the recipient can stop it with STOP

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYesThe number to message, in international format, e.g. +447700900123. Use contacts_find to turn a name into one
textYesWhat to say. A text is charged per 160-character segment, so brevity is not only good manners
channelNoHow to send it: 'sms' (the default) or 'whatsapp'. WhatsApp only works with somebody who messaged this instance in the last 24 hours — reply on the channel they used

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Changed3 schema fields changed
    • addedInput schema / properties / channel
      Added value: +{
+  "description": "How to send it: 'sms' (the default) or 'whatsapp'. WhatsApp only works with somebody who messaged this instance in the last 24 hours — reply on the channel they used",
+  "type": "string"
+}
    • changedInput schema / properties / text / description
      Previous value: -"What to say. Charged per 160-character segment, so brevity is not only good manners"New value: +"What to say. A text is charged per 160-character segment, so brevity is not only good manners"
    • changedInput schema / properties / to / description
      Previous value: -"The number to text, in international format, e.g. +447700900123. Use contacts_find to turn a name into one"New value: +"The number to message, in international format, e.g. +447700900123. Use contacts_find to turn a name into one"
  4. Changed1 schema field changed
    • changedInput schema / properties / to / description
      Previous value: -"The number to text, in international format, e.g. +447700900123. Must be someone in your contacts, a number you have verified as your own, or a number that texted you first"New value: +"The number to text, in international format, e.g. +447700900123. Use contacts_find to turn a name into one"
  5. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations provide only destructiveHint=true, so the description carries the burden of behavioral disclosure. It goes beyond that by detailing cost structure (per-160-character segment, per-24-hour conversation), daily caps, the STOP opt-out mechanism, and the WhatsApp eligibility window. This is substantial context. It doesn't mention failure modes or error responses, but for a messaging tool that's acceptable. No contradiction with the destructiveHint annotation.

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?

The description is about three sentences' worth of content but compressed into one flowing passage. It front-loads the core action and then adds cost/model/eligibility details. Every sentence earns its place: the cost model is essential, the eligibility condition is critical for channel selection, and the cap/STOP info is relevant. Slightly dense but not bloated.

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 mutation tool with cost and deliverability constraints, the description covers the essential operational facts: how to send, channel eligibility, cost model, daily cap, and recipient opt-out. It does not mention authentication or error handling, but those are not typically required for an agent to invoke the tool correctly. The output schema is absent, so no return-value expectations are missing. Overall, it's sufficiently complete.

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%, and the schema already describes each parameter well. The description adds value beyond the schema by explaining cost implications for text length (brevity is not just good manners) and reinforcing the WhatsApp eligibility condition. This helps the agent weigh character count and channel choice. Baseline 3 is elevated because the description provides meaningful use-context for the 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?

The description explicitly states the action ('Message somebody from this instance's number') and the two modes (text or WhatsApp). It distinguishes from siblings like chat_send (which is for chat rooms) and sms_history/sms_number (which are informational). An agent can immediately tell what this tool does without ambiguity.

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 provides clear guidance on when to use WhatsApp versus SMS: WhatsApp only works with someone who messaged the instance in the last 24 hours, and the agent should 'reply on the channel they used'. It also mentions cost implications (per-segment vs per-conversation) and daily caps. It doesn't explicitly name alternatives, but as the only send tool for SMS/WhatsApp, that's adequate. No exclusions are stated, but the channel condition serves as effective guidance.

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

All mu toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources