WhatsApp Business API by Wassenger

send_whatsapp_flow

Send a published WhatsApp Form (Meta WhatsApp Flow) to a chat as a native interactive message: one message instead of asking question after question. Only works within the 24h customer-service window; to start a conversation, send a template whose button opens the form. Pass a token to match the answers to your own record (it comes back in the message:flow:response webhook), and data to prefill the form.

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": {
      "device": "<device>",
      "phone": "<phone>",
      "flow_id": "<flow_id>",
      "cta": "<cta>"
    },
    "name": "send_whatsapp_flow"
  }
}

Input Schema

Name	Required	Description
`cta`	Yes	Text of the button that opens the form (max 30 chars)
`body`	No	Message text shown above the button (max 1024 chars)
`data`	No	Values to prefill the form with, by field name
`phone`	Yes	Recipient phone number in international format (E.164), e.g. +34600111222
`token`	No	Your reference for this send (an order or ticket id). It comes back with the answers.
`device`	Yes	Target WhatsApp device ID (24 character hex string)
`footer`	No	Footer text under the message (max 60 chars)
`header`	No	Header text above the message (max 60 chars)
`screen`	No	Screen to open. If omitted, the form opens on its first screen.
`flow_id`	Yes	The WhatsApp Flow ID to send (flowId from list_whatsapp_flows)
`idempotencyKey`	No	Your unique key for this message, 6 to 36 characters (a UUID works). Reuse the same key when retrying the same message: the API then answers 409 Conflict with the id of the message already created instead of sending it twice. Use a new key for every different message.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026

addedInput schema / properties / idempotencyKey

Added value: +{
+  "description": "Your unique key for this message, 6 to 36 characters (a UUID works). Reuse the same key when retrying the same message: the API then answers 409 Conflict with the id of the message already created instead of sending it twice. Use a new key for every different message.",
+  "maxLength": 36,
+  "minLength": 6,
+  "type": "string"
+}

First observedOct 26, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations supply only openWorldHint=true, so the description carries the behavioral load and does so well: it discloses the 24-hour customer-service window constraint, explains that the token returns via the message:flow:response webhook, and describes prefill behavior. It omits what the call returns on success (no output schema exists), which keeps it from a 5.

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?

A single dense paragraph, front-loaded with what the tool does before the eligibility rule and the token/prefill notes. Every clause carries information, though the long compound sentences could be split for faster scanning.

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 an 11-parameter tool with a nested data object and no output schema, the description covers the critical unknowns: send eligibility, the flow_id source, prefill, and the token round-trip. The main remaining gap is the success response shape, which nothing else in the definition supplies.

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 3 is the baseline, but the description adds meaning the schema doesn't: it names the message:flow:response webhook as the place the token resurfaces and frames data as prefill-by-field-name. That extra wiring context genuinely helps the agent decide what to put in token and data.

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: send a published WhatsApp Form (Meta WhatsApp Flow) into a chat as a native interactive message, with the exact rationale ('one message instead of asking question after question'). This clearly separates it from send_whatsapp_message and from template sends, and it points to list_whatsapp_flows as the source of the flow_id.

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?

Gives an explicit when-not and the alternative: 'Only works within the 24h customer-service window; to start a conversation, send a template whose button opens the form.' That is a real eligibility rule plus a fallback path, so an agent knows when to divert. It falls short of 5 only because the alternative isn't named by its sibling tool name (create_whatsapp_template / send_whatsapp_message).

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

All WhatsApp Business API by Wassenger tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.