Skip to main content
Glama
Sign In

whatsmcp

by com.whatsmcp
OverviewDiscussionsAdmin

Hang Up an AI Voice-Agent Call

wa_ai_call_hangup
DestructiveIdempotent

[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.] End a live AI voice-agent call — one you started with wa_ai_call_start, or an incoming call an agent answered. The call is hung up at once for both sides; its summary, transcript and recording then arrive as for any call (wa_ai_call_get). A call that has already ended is left alone (hung_up false).

Input Schema

NameRequiredDescriptionDefault
call_refYesthe call to end, from wa_ai_call_start or wa_ai_list_calls

Output Schema

NameRequiredDescriptionDefault
nextNowhat to do next
statusNothe call's status as recorded when you asked; it settles to done within a minute of a hangup
hung_upYestrue when the call was live and has been ended; false when it had already ended
refusalNopresent only when the request was declined

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • 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"
  2. Changed1 schema field changed
    • 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"
+  ]
+}
  3. Changed3 schema fields changed
    • 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"
+}
  4. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare a non-read-only, destructive, idempotent operation; the description adds real substance on top: the hangup is immediate for both parties, an already-ended call is left alone and returns hung_up false, and post-call artifacts (summary, transcript, recording) still arrive. It also discloses the plan_required refusal mode and points at wa_get_plan.

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 availability caveat and then the core action, with no filler sentences. The bracketed workspace note is somewhat long but is high-value routing information, so it earns its place.

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?

An output schema and annotations exist, so return-shape explanation is unnecessary; everything else an agent needs — availability precondition, effects on both parties, idempotent no-op behavior, and follow-up read path — is present.

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?

Only one parameter, and schema description coverage is 100% — the schema already says call_ref comes from wa_ai_call_start or wa_ai_list_calls. The description repeats the same provenance without adding format or edge-case detail, so the 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 — end a live AI voice-agent call — and scopes it to both agent-started calls (wa_ai_call_start) and agent-answered incoming calls. It is clearly distinguishable from wa_ai_call_get (read results) and wa_ai_call_start (begin a call).

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?

It gives the operative condition (there is a live call to end) and routes result-reading to wa_ai_call_get and plan-checking to wa_get_plan, plus a workspace availability caveat. It does not spell out an explicit 'do not use this if…' exclusion beyond the plan note, so it is a strong 4 rather than a 5.

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

All whatsmcp 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