react_to_messageReact to a WhatsApp message with a single emoji, or clear your reaction by passing an empty string.
React to a message with one emoji, or pass "" to take your reaction off.
| Name | Required | Description | Default |
|---|---|---|---|
| emoji | Yes | ||
| account_id | No | Account id | |
| message_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| emoji | Yes | ||
| account_id | Yes | ||
| message_id | Yes |
Changes observed during successful MCP inspections.
v1.0.3Input schema / properties / account_id / descriptionPrevious value: -"Registry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account."New value: +"Account id"Input schema / properties / emoji / descriptionRemoved value: -"A single emoji such as \"👍\", or \"\" to remove your reaction"Input schema / properties / message_id / descriptionRemoved value: -"Message id from read_messages / search_messages / get_message, e.g. \"false_4072...@s.whatsapp.net_3EB0...\""Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "account_id": {
+ "type": "string"
+ },
+ "emoji": {
+ "type": "string"
+ },
+ "message_id": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "message_id",
+ "emoji",
+ "account_id"
+ ],
+ "type": "object"
+}v0.15.0Input schema / properties / account_idAdded value: +{
+ "description": "Registry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.",
+ "minLength": 1,
+ "type": "string"
+}v0.9.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds a useful non-obvious behavior: an empty string removes the reaction. It does not, however, state whether an existing reaction is replaced or what happens when removing a reaction that does not exist, leaving part of the behavior to inference.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, tight sentence conveys the primary operation and the important edge-case behavior with no filler. The key constraint is front-loaded and immediately actionable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple three-parameter tool with an output schema and annotations covering idempotence and non-destructiveness, the description is nearly sufficient. It explains the emoji special case and leaves message_id and account_id inferable from their names; a note on the optional account_id's default would make it fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description meaningfully clarifies the emoji parameter: exactly one emoji is allowed, and an empty string requests removal. The schema only describes account_id as 'Account id' and leaves message_id and emoji without descriptions, so the description only partially compensates for the 33% coverage; the remaining parameters rely on their names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a concrete action ('React to a message') with an explicit constraint ('one emoji') and a distinct removal mode ('pass "" to take your reaction off'). This clearly separates it from siblings like send_message, edit_message, and delete_message.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The intended use is implied: call this when you want to add or remove an emoji reaction on a message. However, it names no sibling alternatives and gives no when-not-to-use guidance, so the agent must infer the selection context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.