Skip to main content
Glama
razvangirgiz

wazap-mcp

by razvangirgiz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Transcribe a WhatsApp voice message

transcribe_audio
Read-onlyIdempotent

Convert WhatsApp voice notes and audio messages into text, cache transcripts for repeat calls, and make spoken words searchable and readable in chats.

Instructions

Turn a voice note or an audio message into text. The transcript is cached, so a second call on the same message costs nothing, and from then on the message reads as [voice message · 0:42] "what was said" in read_messages, get_recent_messages and get_message, and its words become searchable through search_messages.

What it costs depends on how the user set transcription up: the local provider (whisper.cpp) is free and the audio never leaves the machine, while the API provider uploads the audio to a third-party service and is billed per minute. Either way this is capped at 10 calls a minute.

TRANSCRIBE_UNAVAILABLE means transcription is off or unfinished on this machine; the fix names the command the user has to run. Do not retry it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
languageNoISO 639-1 code of what is spoken, e.g. "ro"; "auto" detects it. Omit to use the configured default.
account_idNoRegistry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.
message_idYesA message whose type is voice or audio

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.15.0
    • addedInput schema / properties / account_id
      Added value: +{
+  "description": "Registry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.",
+  "minLength": 1,
+  "type": "string"
+}
  2. Addedv0.10.0

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 (readOnly/idempotent/destructive=false) by disclosing caching (a repeat call is free), the cost model (local whisper.cpp free and offline vs API provider uploading audio to a third party and billed per minute), a rate limit (10 calls/minute), and precise error semantics for TRANSCRIBE_UNAVAILABLE with the instruction not to retry. This is exactly the extra behavioral context an agent cannot get from structured fields.

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 paragraphs: what it does and its downstream effect first, then cost/privacy/rate limits, then error handling. Every sentence carries load-bearing information (cache, cost, offline vs upload, rate cap, error fix) with no filler.

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?

No output schema exists, and the description compensates by showing the transcript's rendered form ('[voice message · 0:42] "what was said"') and its searchability. Combined with cost, caching, rate-limit and error coverage, an agent has everything needed to call and interpret this tool.

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 language, account_id and message_id are already documented in the schema (defaults, resolution order, ISO codes, accepted message types). The description adds no parameter-specific syntax or format detail beyond that, so the baseline of 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 (turn into text) and resource (voice note / audio message), which is a distinct operation from siblings like download_media or read_messages. An agent can immediately tell this is the speech-to-text conversion tool and not a media-download or message-reader.

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?

Clear context for use (voice/audio messages) and it spells out the downstream effect in read_messages, get_recent_messages, get_message and search_messages, plus explicit when-not guidance: do not retry on TRANSCRIBE_UNAVAILABLE. It stops short of naming a concrete alternative tool or a prerequisite chain, so it is clear context rather than fully explicit when/when-not/alternatives.

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