Turbo Notify: WhatsApp for AI agents

Send a text message

send_text

Send a WhatsApp text message.

Set exactly one recipient: number, group_id, or contact_id.

Writing @<number> in the text mentions that person, for example @5511999999999. The platform detects it automatically; there is no separate mentions argument.

This is also how to answer the message you just received: a normal message to its sender, as a person does in a chat, with no quote. Quote (quoted_message_id, or reply_to_message) only an earlier message that your answer depends on.

A text message you sent can be corrected later with edit_text_message.

Like a person opening the chat, the number first appears online and its unread messages in that conversation are marked as read, then the message is sent. Opening the conversation this way is automatic and uses no quota of its own.

Returns the new message_id and its initial status. Delivery happens asynchronously; poll get_message_status or watch list_events for the outcome.

Input Schema

Name	Required	Description	Default
`text`	Yes	The message text, 1 to 4096 characters. Write `@<number>` to mention someone.
`number`	No	Recipient phone number in E.164 form, digits only, country code first (e.g. `5511999999999`). Set exactly one of `number`, `group_id` or `contact_id`.
`group_id`	No	Recipient group id (`grp_…`), from `list_groups`. A group id belongs to one number: an id from one inbox does not address the same group in another. Set exactly one of `number`, `group_id` or `contact_id`. Addressing a group needs a plan that includes group messaging: without it the call answers `payment_required: feature_not_available`, and retrying will not change that.
`contact_id`	No	Recipient contact id (`ct_…`), from `list_contacts`. A contact id belongs to one number: an id from one inbox does not address the same person in another. Set exactly one of `number`, `group_id` or `contact_id`.
`number_alias`	No	Which of the organization's WhatsApp numbers this acts on: `main`, the alias of an extra number, or the number's `id` (`num_…`), which stays the same when the alias is renamed. Call `list_numbers` to see them. Defaults to the main number.	main
`idempotency_key`	No	Any printable ASCII text you choose, 1 to 255 characters, for example the id of the event you are answering. Reusing it for the same number suppresses a duplicate if you retry. Without it, retrying after a timeout may deliver the message twice, and the recipient sees both.
`quoted_message_id`	No	Quote an earlier message (`msg_…`) so it appears above yours. Do this only when your text depends on something said a while ago, yours or theirs; do not quote the message you are answering right now, send a normal message instead.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Beyond the annotations, it discloses a real side effect the schema does not: opening the conversation brings the number online and marks unread messages in that chat as read, without consuming quota. It also discloses asynchronous delivery and the duplicate-on-retry risk. The only gap is that quota/pricing and failure modes for unsupported recipients aren't covered in the description (group plan errors live in the schema instead).

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-loaded with the one-line purpose, then short paragraphs each covering a distinct concern (recipient, mentions, quoting, editing, side effects, returns). Slightly long, and the "like a person opening the chat" analogy plus the online/read-marking sequence takes more words than the behavior strictly needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter open-world write tool this is complete: recipient rules, mention syntax, quoting policy, side effects, retry safety, and the return value plus how to observe async delivery. Output schema exists, so the brief note about `message_id` and status is sufficient rather than required.

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; the description earns an increment by clarifying that mentions are parsed inline as `@<number>` and need no separate argument, and by framing quote-vs-normal-message semantics rather than just restating parameter names.

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?

Opens with a specific verb plus resource ("Send a WhatsApp text message") that cleanly separates it from send_media, send_location, send_contact_card, and reply_to_message. The follow-on guidance about quoting and editing further sharpens the boundary against reply_to_message and edit_text_message.

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 selection rules: exactly one of `number`/`group_id`/`contact_id`, don't quote the message currently being answered, quote only when the answer depends on an earlier message, and use `edit_text_message` to correct a sent message. It also tells the agent to poll `get_message_status` or `list_events` rather than assume delivery.

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

All Turbo Notify: WhatsApp for AI agents 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.