whatsmcp

Start an AI Voice-Agent Call

wa_ai_call_start

[Not usable in this workspace: it acts on every number, and not every number's plan includes it — calling it returns a plan_required refusal; wa_get_plan lists each number's plan.] Have an AI voice agent call a WhatsApp number from one of your numbers, using a preset from wa_ai_list_presets. Pass per-call context in variables. Returns immediately with a call_ref; the call then rings and runs on its own. Poll wa_ai_call_get about every 30 seconds until status is done, failed, no_answer or busy — then it carries the summary, transcript, collected data and a recording link. One call at a time per number; a number that just finished a call must wait a moment. A call to a number that is not in the calling line's contacts is refused with reason recipient_not_contact so you do not cold-call a stranger by accident; set force=true to call anyway (this does not apply to Business/WABA lines).

Input Schema

Name	Required	Description
`to`	Yes	the WhatsApp number to call, international format, e.g. +447700900123
`force`	No	set true to call a number that is NOT in this line's contacts; without it such a call is refused with reason recipient_not_contact so you do not cold-call a stranger by accident. No effect when the calling line is a Business (WABA) number
`preset`	Yes	the preset name, from wa_ai_list_presets
`variables`	No	per-call context for the agent: flat string/number/boolean values, merged over the preset's defaults, e.g. {"customer_name":"Ann","order_id":"A-1042"}
`first_message`	No	override what the agent says first on this call

Output Schema

Name	Required	Description
`next`	No	what to do next
`status`	No	dialing once accepted
`refusal`	No	present only when the call was not placed
`call_ref`	No	pass to wa_ai_call_get to follow the call

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedOutput schema / properties / refusal / properties / account_status / description

Previous value: -"when the number is not working: its status — starting, not_running, whatsapp_down, suspended, pairing, unlinked or locked"New value: +"when the number is not working: its status — starting, not_running, whatsapp_down (telegram_down for a Telegram account), suspended, pairing, unlinked or locked"

Changed1 schema field changedNov 1, 2026

addedInput schema / properties / force

Added value: +{
+  "description": "set true to call a number that is NOT in this line's contacts; without it such a call is refused with reason recipient_not_contact so you do not cold-call a stranger by accident. No effect when the calling line is a Business (WABA) number",
+  "type": "boolean"
+}

Changed1 schema field changedOct 26, 2026

addedOutput schema / properties / refusal / properties / candidates

Added value: +{
+  "description": "on an account_ambiguous refusal: the accounts to choose from — retry with one of these as account_id",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "account_id": {
+        "description": "the id to retry with as account_id",
+        "type": "string"
+      },
+      "name": {
+        "description": "the account's WhatsApp display name",
+        "type": "string"
+      },
+      "phone": {
+        "description": "the account's phone number, E.164",
+        "type": "string"
+      },
+      "status": {
+        "description": "whether the number works right now — live, connecting, or why not, as wa_list_accounts reports it",
+        "type": "string"
+      }
+    },
+    "required": [
+      "account_id"
+    ],
+    "type": "object"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

Changed3 schema fields changedOct 14, 2026

addedOutput schema / properties / refusal / properties / account_status

Added value: +{
+  "description": "when the number is not working: its status — starting, not_running, whatsapp_down, suspended, pairing, unlinked or locked",
+  "type": "string"
+}

addedOutput schema / properties / refusal / properties / account_status_reason

Added value: +{
+  "description": "the detail of account_status, e.g. no_egress, stopped, no_plan",
+  "type": "string"
+}

addedOutput schema / properties / refusal / properties / since

Added value: +{
+  "description": "when the number stopped working, RFC3339, when known",
+  "type": "string"
+}

First observedSep 27, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare non-read-only, non-idempotent, non-destructive; the description adds substantially more: asynchronous immediate return with a call_ref, the poll cadence and terminal statuses, the result payload contents, one-call-at-a-time-per-number plus a post-call cooldown, and the recipient_not_contact guard with its force override and WABA exception. It also discloses the workspace-level plan_required refusal, which is the single most important behavior for an agent to know before invoking.

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-loading the 'not usable in this workspace' caveat is exactly right, and every sentence carries information: purpose, workflow, constraints, safety guard. The cost is a dense single paragraph of roughly 130 words with several semicolon-chained clauses, which could be broken into bullets for faster scanning.

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 an asynchronous, side-effecting tool this is complete: it explains the immediate return, how to follow up, what the terminal statuses are, what the result contains, and the concurrency/cooldown limits. An output schema exists so return values need no further explanation, and the description covers everything an agent needs to call and then correctly follow up.

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%, so the parameters are already fully documented, including the force guard and the variables example. The description reinforces the key ones ('Pass per-call context in variables', preset from wa_ai_list_presets) but adds little syntax or semantics the schema does not already carry. Baseline 3 is appropriate.

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: have an AI voice agent call a WhatsApp number from one of your numbers using a named preset. It distinguishes itself from the related siblings by naming wa_ai_list_presets (source of the preset), wa_ai_call_get (the polling counterpart) and wa_get_plan (the plan lookup). An agent can tell exactly what this tool is versus wa_ai_call_get or wa_ai_call_hangup.

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 when-to-use and when-not-to-use: it first warns the tool returns a plan_required refusal in this workspace and points to wa_get_plan. It then spells out the full call lifecycle ('Returns immediately with a call_ref... Poll wa_ai_call_get about every 30 seconds until status is done, failed, no_answer or busy') and the alternatives for continuing the workflow.

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

All whatsmcp 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.

Resources

Need Help?