CallMCP — Phone Call MCP Server

Send Message

send_message

Destructive

Send one message to a business's customer on the channel you choose: a text (sms) from one of the business's agent lines, or a WhatsApp message from its connected WhatsApp number. The same consent, Do-Not-Call, quiet-hours and rate gates as the dashboard apply, and a refusal says which one. sms needs from_agent_id; whatsapp needs a number the owner connected to WhatsApp (pass from when there is more than one) and a customer who messaged that number in the last 24 hours. Email is not sent here; draft_email_campaign drafts a campaign the owner reviews and approves. business_id is required when the account has more than one business. The result reports that the provider accepted the message, not that it was delivered.

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": {
      "channel": "<channel>",
      "to": "<to>",
      "body": "<body>"
    },
    "name": "send_message"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	Recipient: an E.164 phone number.
`body`	Yes	Message text.
`from`	No	whatsapp only: the business's connected WhatsApp number, when it has more than one.
`channel`	Yes
`lead_id`	No	Optional lead ID to link and honor the lead's automation-pause state.
`business_id`	No	The business sending. Required when the account has more than one.
`from_agent_id`	No	sms only (required): the agent whose phone line sends the text.
`idempotency_key`	No	Optional caller-supplied key. Completed replays return the original send. New keyed WhatsApp requests reserve a durable intent before dispatch. Uncertain or concurrent replays are refused, and a new key is treated as a new send. Legacy lost receipts remain unverified.

Output Schema

Name	Required	Description
`id`	No
`to`	No
`code`	No
`from`	No
`error`	No	Present when success is false
`status`	No
`channel`	No
`success`	Yes	Whether the tool completed successfully
`provider`	No
`replayed`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well past the annotations by disclosing the consent, Do-Not-Call, quiet-hours and rate gates, the 24-hour messaging window, and the crucial semantic that success means provider acceptance rather than delivery. This adds real context to destructiveHint=true and openWorldHint=true, telling the agent what can go wrong and why a call may be refused.

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 core action and channel split is front-loaded, and the exclusions and delivery caveat come after. It is dense and the WhatsApp sentence is long enough to be a run-on, but nearly every clause carries distinct operational meaning.

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?

Covers everything an agent needs before a destructive, open-world send: required inputs per channel, eligibility windows, gating behavior, and the meaning of a success result. With an output schema present, no further return-value explanation is owed.

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 already 88%, so the schema carries most parameter documentation. The description still adds conditional logic the schema only states flatly: which fields are channel-specific, when from and business_id become required, and the 24-hour WhatsApp eligibility rule that no parameter documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Send one message to a business's customer') and splits the two channels it covers with their distinct source lines. It cleanly excludes email by pointing at draft_email_campaign, but it never clarifies its relationship to the overlapping sibling send_sms, so an agent choosing between the two SMS paths gets no help.

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?

Gives explicit per-channel preconditions: sms requires from_agent_id, whatsapp requires an owner-connected number and a customer who messaged within 24 hours, from is needed only with multiple numbers, and business_id only with multiple businesses. It also names when not to use it (email goes to draft_email_campaign) and warns that refusals identify which gate blocked the send.

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

All CallMCP — Phone Call MCP Server tools Inspect

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.