Skip to main content
Glama
billyfranklim1

mcp-evolution

Send Audio

send_audio

Transmits an audio voice note to a WhatsApp recipient or group using a URL or base64 encoding.

Instructions

Send a WhatsApp audio (PTT voice note) via the pinned instance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
numberYesRecipient JID or phone number (e.g. 5511999999999 or group@g.us)
audioYesURL or base64-encoded audio (ogg/opus preferred for WhatsApp)
encodingNoSet true if audio is base64 encoded
delayNoDelay in milliseconds before sending

Implementation Reference

  • The handler for the 'send_audio' tool. Registers the tool with the MCP server, accepting args (number, audio, encoding, delay), posts to /message/sendWhatsAppAudio/{instanceName}, and returns the response as JSON.
    export function registerSendAudio(server: McpServer, client: EvolutionClient): void {
      server.registerTool(
        "send_audio",
        {
          title: "Send Audio",
          description: "Send a WhatsApp audio (PTT voice note) via the pinned instance.",
          inputSchema: schema,
        },
        async (args) => {
          try {
            const payload: Record<string, unknown> = { number: args.number, audio: args.audio };
            if (args.encoding !== undefined) payload["encoding"] = args.encoding;
            if (args.delay !== undefined) payload["delay"] = args.delay;
            const data = await client.post(`/message/sendWhatsAppAudio/${client.instanceName}`, payload);
            return { content: [{ type: "text" as const, text: JSON.stringify(data, null, 2) }] };
          } catch (e) {
            if (e instanceof McpError) return { isError: true, content: [{ type: "text" as const, text: e.message }] };
            throw e;
          }
        }
      );
    }
  • Input schema defining 'number' (PhoneOrJidSchema), 'audio' (URL/base64 audio string), 'encoding' (optional boolean), and 'delay' (optional number in ms).
    const schema = {
      number: PhoneOrJidSchema,
      audio: z.string().min(1).describe("URL or base64-encoded audio (ogg/opus preferred for WhatsApp)"),
      encoding: z.boolean().optional().describe("Set true if audio is base64 encoded"),
      delay: z.number().int().nonnegative().optional().describe("Delay in milliseconds before sending"),
    };
  • Registration call: registerSendAudio(server, client) invoked inside registerAllTools.
    registerSendAudio(server, client);
  • Import of registerSendAudio from ./send-audio.js in the main tools index.
    import { registerSendAudio } from "./send-audio.js";
  • PhoneOrJidSchema helper used by the send-audio tool schema to validate the recipient field.
    export const PhoneOrJidSchema = z
      .string()
      .min(1)
      .describe("Recipient JID or phone number (e.g. 5511999999999 or group@g.us)");
Behavior2/5

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

With no annotations, the description carries full burden. It does not disclose behavioral traits such as synchronous/asynchronous execution, rate limits, authentication requirements, or what happens on failure. The description is too brief.

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?

Single sentence, direct and to the point. No unnecessary words or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 4 parameters and no output schema, the description is moderately complete. It lacks details on success/error returns, but the schema provides adequate parameter info. Could be improved by adding minimal behavioral context.

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 100%, so baseline is 3. The description adds minimal value beyond the schema; it only reiterates 'audio (PTT voice note)' without further detail on parameters like delay or encoding.

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 clearly states the action (send), the specific resource (WhatsApp audio/PTT voice note), and the context (via pinned instance). It distinguishes from sibling tools like send_media by specifying 'audio (PTT voice note)'.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives (e.g., send_media for other media types). No prerequisites, exclusions, or context provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/billyfranklim1/mcp-evolution'

If you have feedback or need assistance with the MCP directory API, please join our Discord server