Skip to main content
Glama
wazap-mcp

wazap-mcp

by razvangirgiz

Send a drafted WhatsApp message

confirm_send
Idempotent

Send an approved WhatsApp draft to its intended recipient exactly once, re-preview when approval is unclear or the draft is stale, and never resend after an unknown send outcome.

Instructions

Send a draft the user approved — this text, this recipient: the only call that sends, once per draft. A yes about something else: show the preview again and ask. Expired, missing or stale: draft again, show the new preview, ask again. SEND_OUTCOME_UNKNOWN: read_messages, never redo it unasked.

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": {
      "draft_id": "<draft_id>"
    },
    "name": "confirm_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
draft_idYesFrom send_message; one with send_at is scheduled, not sent
account_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.7.4
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  2. Changed1 schema field changedv1.6.0
    • removedInput schema / properties / account_id / description
      Removed value: -"Account id"
  3. Changed1 schema field changedv1.4.0
    • changedInput schema / properties / draft_id / description
      Previous value: -"From send_message"New value: +"From send_message; one with send_at is scheduled, not sent"
  4. Changed2 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"
    • changedInput schema / properties / draft_id / description
      Previous value: -"The draft_id returned by a send_* tool"New value: +"From send_message"
  5. Addedv0.15.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true), and the description's 'once per draft' and 'never redo it unasked' are consistent with the idempotency hint rather than contradicting it. It adds genuinely useful incident behavior — what to do when the send outcome is unknown, and how stale drafts are handled — but says nothing about what a successful send returns or how to confirm delivery. Note: annotations declare idempotentHint=true while the text warns against repeating an unconfirmed send, which is a nuance, not a contradiction.

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?

Front-loads the action and its condition, then enumerates exception paths in short, distinct clauses — no wasted sentences. The telegraphic, fragment-heavy register ('A yes about something else', 'Expired, missing or stale') trades a little readability for density.

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?

For a mutation tool with no output schema and moderate annotation coverage, the description covers preconditions, the ambiguous-outcome recovery path, and stale-draft handling. The gap is account_id (unknown in both schema and description) and any description of the success response, which leaves the agent guessing about the return shape after a confirmed send.

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

Parameters2/5

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

Only 50% of parameters are documented in the schema, so the description should carry the rest. It never mentions account_id, and the schema's note that a draft_id with send_at is 'scheduled, not sent' is the only real parameter semantics available. 'this text, this recipient' gestures at what the draft pins down but adds no usable detail about either field.

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 and resource ('Send a draft the user approved') plus a uniqueness claim ('the only call that sends, once per draft') that separates it from draft-producing calls. The claim sits in mild tension with the sibling named send_message, which the schema (draft_id 'From send_message') implies only drafts; an agent reading both gets there, but the description alone doesn't resolve the overlap explicitly.

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?

Gives explicit branching guidance: a yes about something else means re-show preview and ask, expired/missing/stale means re-draft and re-confirm, and SEND_OUTCOME_UNKNOWN means call read_messages and never redo unasked. It names the alternative tool for the ambiguous-outcome path and states the precondition (user approval of this text and this recipient).

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