Skip to main content
Glama
wazap-mcp

wazap-mcp

by razvangirgiz

Manage a WhatsApp chat

manage_chat
Destructive

Preview and confirm WhatsApp chat actions—archive, pin, mute, mark read/unread, pin or star messages, clear, delete, block, or unblock—before applying changes.

Instructions

Preview archive, pin, mute, pin_message, star_message, clear, delete, block and undo. After approval repeat chat_id/action with confirmation_id, without options. Expires in 15m; one attempt. mark_read runs directly, only when the user asks.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "chat_id": "<chat_id>",
      "action": "<action>"
    },
    "name": "manage_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
chat_idYesChat id, or a phone number
pin_hoursNopin_message: 168 by default
account_idNo
message_idNopin_message, star_message and their undo; in chat_id
mute_hoursNomute: 8 by default
confirmation_idNoFrom preview; omit message/duration options

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.7.4
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • addedInput schema / properties / pin_hours / anyOf
      Added value: +[
      +  {
      +    "const": 24,
      +    "type": "number"
      +  },
      +  {
      +    "const": 168,
      +    "type": "number"
      +  },
      +  {
      +    "const": 720,
      +    "type": "number"
      +  }
      +]
    • removedInput schema / properties / pin_hours / enum
      Removed value: -[
      -  24,
      -  168,
      -  720
      -]
    • removedInput schema / properties / pin_hours / type
      Removed value: -"number"
  2. Changed2 schema fields changedv1.6.0
    • removedInput schema / properties / account_id / description
      Removed value: -"Account id"
    • addedInput schema / properties / confirmation_id
      Added value: +{
      +  "description": "From preview; omit message/duration options",
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
  3. Changed6 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 / action / description
      Removed value: -"What to do with the chat"
    • changedInput schema / properties / chat_id / description
      Previous value: -"Chat id as returned by another tool (\"<digits>@s.whatsapp.net\" or \"<id>@g.us\"), or a phone number in international format"New value: +"Chat id, or a phone number"
    • changedInput schema / properties / message_id / description
      Previous value: -"The message for pin_message, unpin_message, star_message and unstar_message; it must be in chat_id"New value: +"pin_message, star_message and their undo; in chat_id"
    • changedInput schema / properties / mute_hours / description
      Previous value: -"Hours to mute, default 8; only used by \"mute\""New value: +"mute: 8 by default"
    • changedInput schema / properties / pin_hours / description
      Previous value: -"How long pin_message keeps the message pinned: 24, 168 (default) or 720 hours"New value: +"pin_message: 168 by default"
  4. Changed3 schema fields changedv0.21.0
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "archive",
      -  "unarchive",
      -  "pin",
      -  "unpin",
      -  "mute",
      -  "unmute",
      -  "mark_read",
      -  "mark_unread"
      -]New value: +[
      +  "archive",
      +  "unarchive",
      +  "pin",
      +  "unpin",
      +  "mute",
      +  "unmute",
      +  "mark_read",
      +  "mark_unread",
      +  "pin_message",
      +  "unpin_message",
      +  "star_message",
      +  "unstar_message",
      +  "clear",
      +  "delete",
      +  "block",
      +  "unblock"
      +]
    • addedInput schema / properties / message_id
      Added value: +{
      +  "description": "The message for pin_message, unpin_message, star_message and unstar_message; it must be in chat_id",
      +  "minLength": 5,
      +  "type": "string"
      +}
    • addedInput schema / properties / pin_hours
      Added value: +{
      +  "description": "How long pin_message keeps the message pinned: 24, 168 (default) or 720 hours",
      +  "enum": [
      +    24,
      +    168,
      +    720
      +  ],
      +  "type": "number"
      +}
  5. 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"
      +}
  6. First observedv0.9.3

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, openWorldHint=true and non-idempotency, so the safety bar is partly met by structured data. The description still adds genuinely new behavioral facts: a preview/approval gate, a 15-minute expiry, a single attempt, and the constraint to omit message/duration options on the confirming call. It does not explain what clear versus delete actually does to data, but the approval-gate disclosure is substantive.

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?

The text is short and front-loads the action set, then the confirmation mechanics, then the mark_read exception. The opening sentence is telegraphic (a bare list of verbs) and slightly cryptic in isolation, but no sentence is redundant.

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 seven-parameter, sixteen-action destructive tool the description covers the workflow and confirmation lifecycle well. It leaves gaps on action semantics that matter for a destructive tool, notably what clear removes versus delete, and what the preview returns to the agent. Adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 71%, so the schema carries most of the per-parameter burden. The description nonetheless adds meaning the schema cannot: confirmation_id originates from the preview step, and on that call the message/duration options must be dropped, plus the 15-minute validity window. That is real added semantics for the most error-prone parameter pairing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource context (a chat) and enumerates the concrete actions available (archive, pin, mute, pin_message, star_message, clear, delete, block and their undo), plus the preview-then-confirm mechanic. It is a specific, actionable statement, though it never states in one clause that this tool mutates chat-level state, leaving the agent to infer that from the action list and title.

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

Usage Guidelines3/5

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

It gives real routing guidance for the two-step flow (preview first, then repeat chat_id/action with confirmation_id and no options) and a clear exception rule: mark_read runs directly and only when the user asks. It does not say when to prefer this over siblings such as manage_group, delete_message or edit_message, so action selection among overlapping tools is only implied.

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