Skip to main content
Glama
razvangirgiz

wazap-mcp

by razvangirgiz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Draft a WhatsApp poll

send_poll

Draft a WhatsApp poll with a question and 2-12 options, preview it, then call confirm_send to deliver it. Votes are cast in WhatsApp and cannot be read back.

Instructions

Draft a poll. Does not send. Participants vote in WhatsApp; wazap cannot read the votes back. Show the preview; after the user says yes, call confirm_send.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chat_idYesChat id as returned by another tool ("<digits>@s.whatsapp.net" or "<id>@g.us"), or a phone number in international format
optionsYesAnswer options (2-12)
questionYesThe poll question
account_idNoRegistry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.
multi_selectNoAllow voters to pick more than one option

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?

Annotations cover safety flags (destructiveHint=false, openWorldHint=true), but the description adds genuinely non-obvious behavior beyond them: the tool drafts rather than sends, and votes are cast in WhatsApp and cannot be read back by wazap. That limitation is valuable context an agent could not infer. It stops short of describing the returned preview payload or whether drafts expire.

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?

Four short sentences, front-loaded with the core fact ('Draft a poll. Does not send.') and ending on the required next action. The line break is slightly awkward but every sentence earns its place.

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 no output schema, the description still conveys that a preview is produced and must be confirmed, which is the key return-value behavior. It leaves the exact preview contents and any draft lifetime unstated, but is otherwise sufficient for correct invocation.

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 chat_id, options, question, account_id, and multi_select are all documented in the schema itself, including the 2-12 option bound and multi-select semantics. The description adds no parameter-level detail beyond that, so the baseline 3 is correct.

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 and resource ('Draft a poll') and immediately disambiguates from the send path by asserting 'Does not send.' An agent can distinguish it from confirm_send and send_message without inspecting any schema.

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?

Prescribes the exact workflow: show the preview, wait for the user to say yes, then call confirm_send. This is an explicit when-to-use plus the named alternative, leaving nothing to inference.

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