Skip to main content
Glama
wsapi-chat

WSAPI WhatsApp MCP Server

by wsapi-chat
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

whatsapp_send_voice

Send a WhatsApp voice note (push-to-talk) from base64 data or a public URL so it appears as a recorded voice message; returns the message ID.

Instructions

Send a voice note (push-to-talk), from base64 data or a public URL; OGG/Opus plays best. It appears as a recorded voice message. For a music or audio file, use whatsapp_send_audio. Not idempotent. Returns the message ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYesRecipient JID
urlNoURL of the voice file
dataNoBase64 encoded voice data
replyToNo
mentionsNo
mimeTypeNoMIME type (auto-detected if omitted)
viewOnceNo
isForwardedNo
replyToSenderIdNo
ephemeralExpirationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changedv2.0.0
    • addedInput schema / properties / data
      Added value: +{
+  "description": "Base64 encoded voice data",
+  "type": "string"
+}
    • addedInput schema / properties / ephemeralExpiration
      Added value: +{
+  "enum": [
+    "off",
+    "24h",
+    "7d",
+    "90d"
+  ],
+  "type": "string"
+}
    • removedInput schema / properties / isForwarded / description
      Removed value: -"Whether the message should be marked as forwarded"
    • removedInput schema / properties / isForwarded / optional
      Removed value: -true
    • removedInput schema / properties / mentions / description
      Removed value: -"List of phone numbers to mention"
    • removedInput schema / properties / mentions / optional
      Removed value: -true
    • addedInput schema / properties / mimeType
      Added value: +{
+  "description": "MIME type (auto-detected if omitted)",
+  "type": "string"
+}
    • removedInput schema / properties / replyTo / description
      Removed value: -"ID of the message being replied to"
    • removedInput schema / properties / replyTo / optional
      Removed value: -true
    • addedInput schema / properties / replyToSenderId
      Added value: +{
+  "type": "string"
+}
    • changedInput schema / properties / to / description
      Previous value: -"Recipient phone number (with @s.whatsapp.net) or group ID (with @g.us)"New value: +"Recipient JID"
    • addedInput schema / properties / url
      Added value: +{
+  "description": "URL of the voice file",
+  "type": "string"
+}
    • removedInput schema / properties / viewOnce / description
      Removed value: -"Whether the voice message should be sent as view-once"
    • removedInput schema / properties / viewOnce / optional
      Removed value: -true
    • removedInput schema / properties / voiceBase64
      Removed value: -{
-  "description": "Base64 encoded voice data (alternative to voiceURL)",
-  "optional": true,
-  "type": "string"
-}
    • removedInput schema / properties / voiceURL
      Removed value: -{
-  "description": "URL of the voice file to send (alternative to voiceBase64)",
-  "optional": true,
-  "type": "string"
-}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true. The description adds value beyond these by explicitly stating 'Not idempotent' and naming the return value ('Returns the message ID'), which the annotation only flags as a hint. It also discloses presentation semantics ('appears as a recorded voice message'). It does not cover auth requirements or rate limits, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no waste: what it does, when to use the alternative, and key behavioral traits (non-idempotent, returns message ID). The most actionable information is front-loaded.

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 send tool with no output schema, the description adequately covers purpose, sibling differentiation, input modes, format guidance, and the key behavioral fact (non-idempotent). It falls short of complete because it doesn't touch the 60% of undocumented parameters (reply/forward/mentions/viewOnce/ephemeral) which an agent would need to fully exploit, but it is complete enough to call correctly for the primary use cases.

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 coverage is 40%, so 6 of 10 parameters (replyTo, mentions, viewOnce, isForwarded, replyToSenderId, ephemeralExpiration) are undocumented in both the schema and the description. The description does explain the two primary mutually exclusive input methods (url vs data) and the format hint (OGG/Opus), which adds value over the schema's bare descriptions, but does not compensate for the coverage gap. 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 ('Send a voice note (push-to-talk)') and explicitly names the sibling it is not (whatsapp_send_audio for music/audio files). An agent can distinguish this from whatsapp_send_audio and whatsapp_send_document without opening schemas.

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?

Explicitly names the alternative (whatsapp_send_audio) and the condition selecting it ('For a music or audio file'). It also states the two input modes (base64 data or public URL) and the format preference (OGG/Opus plays best), giving clear when-to-use guidance.

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

Deploy Server

Other Tools