Skip to main content
Glama
razvangirgiz

wazap-mcp

by razvangirgiz

Delete a WhatsApp message

delete_message
DestructiveIdempotent

Delete a WhatsApp message after user confirmation. Choose to retract it for everyone within 2 days or remove it only from the linked account's devices.

Instructions

Delete a message; confirm with the user first. for_everyone: true retracts it for everyone within 2 days: the account's own message, or anyone's in a group where it is admin. for_everyone: false removes any message from the linked account's devices only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
account_idNoAccount id
message_idYes
for_everyoneYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
account_idYes
message_idYes
for_everyoneYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.0.3
    • changedInput schema / properties / account_id / description
      Previous value: -"Registry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account."New value: +"Account id"
    • removedInput schema / properties / for_everyone / description
      Removed value: -"Required. true retracts it for everyone in the chat; false deletes it for the linked account only"
    • removedInput schema / properties / message_id / description
      Removed value: -"Message id from read_messages / search_messages / get_message, e.g. \"false_4072...@s.whatsapp.net_3EB0...\""
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "account_id": {
      +      "type": "string"
      +    },
      +    "for_everyone": {
      +      "type": "boolean"
      +    },
      +    "message_id": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "message_id",
      +    "for_everyone",
      +    "account_id"
      +  ],
      +  "type": "object"
      +}
  2. Changed3 schema fields changedv0.21.0
    • removedInput schema / properties / for_everyone / default
      Removed value: -false
    • changedInput schema / properties / for_everyone / description
      Previous value: -"Retract for all participants (WhatsApp supports no other kind of delete here)"New value: +"Required. true retracts it for everyone in the chat; false deletes it for the linked account only"
    • changedInput schema / required
      Previous value: -[
      -  "message_id"
      -]New value: +[
      +  "message_id",
      +  "for_everyone"
      +]
  3. 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"
      +}
  4. First observedv0.9.3

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructive behavior, but the description adds meaningful context: the 2-day retraction window, the admin-permission condition for group messages, and that for_everyone:false only affects the linked account's devices. This goes well beyond the structured hints and helps set expectations.

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 clauses with no filler; the mandatory user-confirmation is front-loaded, and the for_everyone branch is expressed compactly. Every sentence adds distinct value.

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?

With a rich behavioral description and an output schema present, the core invocation requirements are covered. The main remaining gap is that account_id's role is never explained, and there's no explicit statement of what happens if it is omitted. Still, for a destructive tool with strong annotations, this is close to complete.

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?

The description thoroughly explains for_everyone behavior, which the schema leaves undocumented, and indirectly clarifies message scope as 'the account's own message' or 'anyone's in a group.' However, account_id and message_id receive no real semantic help beyond the schema's minimal 'Account id' and name/minLength, so the compensation is incomplete.

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 uses a specific verb and resource ('Delete a message') and immediately clarifies the operation's scope via the for_everyone flag. The local-vs-everyone distinction separates it from siblings like edit_message and send_message even though those aren't named.

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 explicitly instructs the agent to confirm with the user first, which is a clear prerequisite before invoking. It also states when for_everyone is valid (true within 2 days, own message or admin in group) versus local-only removal (false), giving condition-based guidance. It doesn't explicitly name alternative tools, but it defines the choice space.

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