Skip to main content
Glama
razvangirgiz

wazap-mcp

by razvangirgiz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Manage a WhatsApp group

manage_group
Destructive

Administer WhatsApp group: add/remove/promote/demote participants, set subject/description, get/revoke invite links. Requires admin rights; check group info first.

Instructions

Administer a group. Actions:

  • add / remove / promote / demote — need participant_ids; each participant comes back with status ok, invite_needed or failed

  • leave — DESTRUCTIVE, rejoining needs an invite

  • set_subject / set_description — need value

  • get_invite_link / revoke_invite_link

Everything except leave requires the linked account to be a group admin; call get_group_info first to check.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
valueNoNew subject or description
actionYesGroup action to perform
group_idYesGroup chat id ("<id>@g.us")
account_idNoRegistry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.
participant_idsNoTargets of add/remove/promote/demote

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. First observedv0.9.3

TDQS

A4.3/5.0
Behavior4/5

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

Goes beyond the annotations by documenting the per-participant result statuses (ok, invite_needed, failed), the irreversible consequence of leave, and the admin-permission requirement. Annotations already cover the safety profile (destructiveHint, idempotentHint), so this extra operational detail is genuinely additive; only return shape for the non-participant actions is undocumented.

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?

Front-loaded one-line purpose followed by a dense action list; every line carries either a parameter requirement or a behavioral warning. No filler sentences.

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 5 parameters, no output schema, and mutation semantics, the description supplies the prerequisites, destructive caveat, and partial result semantics an agent needs. Gaps are minor: no description of what get_invite_link returns or how failures for non-participant actions surface.

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 100%, so the baseline is 3, but the description maps actions to their required parameters ('add / remove / promote / demote — need participant_ids', 'set_subject / set_description — need value'), which the schema alone does not express. That action-to-parameter binding is real added value.

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?

States a specific verb+resource ('Administer a group') and then enumerates the exact action set (add/remove/promote/demote/leave/set_subject/set_description/get_invite_link/revoke_invite_link), so an agent immediately knows the tool's scope. It does not explicitly distinguish itself from siblings like create_group or get_group_info, though the enum implicitly excludes creation.

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 states the precondition ('Everything except leave requires the linked account to be a group admin') and prescribes a routing step ('call get_group_info first to check'). It also warns that leave is destructive and rejoining needs an invite, giving clear when/when-not 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