KaiCalls

Send SMS

send_sms

Destructive

Send an outbound text message from one of your agents' phone lines to a recipient, routed through the governed messaging API. Compliance gates (opt-out / Do-Not-Call / quiet-hours), rate limits, and message logging all apply. Provide from_agent_id (the sending agent), to (recipient phone in E.164), and message. Optionally link lead_id to attribute the text and respect that lead's automation-pause state.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	Yes	Recipient phone number in E.164 format (e.g. +18135551234).
`lead_id`	No	Optional lead ID to link and honor the lead's automation-pause state.
`message`	Yes	Text message body.
`from_agent_id`	Yes	Agent ID whose phone line the text is sent from.
`idempotency_key`	No	Optional caller-supplied key. A replay with the same key returns the original send outcome instead of sending again — use it when retrying after an uncertain response.

Output Schema

TableJSON Schema

Name	Required	Description
`to`	No
`from`	No
`error`	No	Present when success is false
`success`	Yes	Whether the tool completed successfully
`message_sid`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 21, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "Optional caller-supplied key. A replay with the same key returns the original send outcome instead of sending again — use it when retrying after an uncertain response.",
+  "type": "string"
+}

AddedJun 26, 2026

TDQS

A3.9/5.0

Behavior4/5

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

The description discloses behavior beyond the annotations: compliance gates (opt-out / Do-Not-Call / quiet-hours), rate limits, message logging, and the side effect of honoring a lead's automation-pause state when lead_id is supplied. These add meaningful context on top of readOnlyHint=false / destructiveHint=true, which only signal that the call has side effects without describing what they are.

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?

Three sentences with a clear front-loaded action, a compliance caveat, and a parameter walkthrough. The third sentence partially duplicates the schema's parameter descriptions, but the first sentence is pure signal and the second earns its place by surfacing the governed-messaging context.

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?

The definition is complete enough given the scaffolding: an output schema exists (so return values are covered elsewhere), the input schema is fully documented, and annotations already convey safety/destructiveness. The description adds the compliance and logging context an agent needs to anticipate failed sends, while idempotency_key semantics are left to the schema, which is acceptable.

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?

With schema description coverage at 100%, the baseline is 3. The narrative mostly restates what the schema already says (from_agent_id = sending agent, to = E.164, lead_id = automation-pause), adding little new meaning. It does cluster the key parameters into a call-to-action sentence, which slightly eases comprehension, but not enough to exceed the baseline.

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 opens with a specific verb-plus-resource statement: "Send an outbound SMS from one of your agents' phone lines to a recipient," which distinguishes it from siblings like make_call (voice) and list_sms_messages (read-only listing). The governed-messaging-API detail further positions it uniquely among the 80+ tools.

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

Usage Guidelines3/5

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

The description implies when the tool is used (sending agent-originated SMS under compliance constraints) and states the operating environment, but it never explicitly routes the agent to alternative tools or says when NOT to use it (e.g., vs make_call for voice, or list_sms_messages for retrieval). No sibling tool is named, so the agent must infer the boundary from purpose alone.

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

All KaiCalls tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.