WA MCP

react_to_message

Idempotent

Reacts to a WhatsApp message with an emoji (like tapping and holding a message on the phone), in a 1:1 chat or a group, on the other person's messages or the user's own. Paid plan only: on the free plan the call is refused with a note on how to subscribe. Pass the message's id from read_chat_history or search_messages; the chat, the sender and whether the user sent it are looked up automatically. A new reaction replaces the user's previous one on that message; pass emoji "" to remove it. Everyone in the chat sees the reaction, so confirm with the user first unless they asked for it. Returns { message_id, status (reacted, removed or failed), emoji, chat, error? }: chat is the conversation, with the contact fields (name; name_source: address_book, push_name, group_subject, business, phone or unresolved; canonical_jid: the JID to pass to send_message and read_chat_history; phone_jid and lid_jid: the chat's phone-number and LID forms, null when unknown or for groups; phone_display: the number as +). If the message can't be found, the error asks for chat_jid (and from_me or sender_jid); pass them only then.

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": {
      "message_id": "<message_id>",
      "emoji": "<emoji>"
    },
    "name": "react_to_message"
  }
}

Input Schema

Name	Required	Description
`emoji`	Yes	One emoji, e.g. 👍 ❤️ 😂 😮 😢 🙏. An empty string "" removes the user's reaction.
`from_me`	No	Optional, only if the message isn't found: true if the user sent it (read_chat_history shows it from "Me").
`chat_jid`	No	Optional, only if the message isn't found: the chat it is in (JID or phone number).
`message_id`	Yes	The message `id` from read_chat_history or search_messages. Not a reaction's own id.
`sender_jid`	No	Optional, only if the message isn't found and is in a group: its `sender_jid` from read_chat_history.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say non-read-only, idempotent, open-world; the description adds far more: a paid-plan gate with refusal behavior on free plan, social visibility ("Everyone in the chat sees the reaction"), replace-instead-of-stack semantics, and empty-emoji removal. It also enumerates the return payload including the error branch, which annotations cannot convey.

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 purpose, then behavior, then return shape, then the error escape hatch – a sensible order with no filler sentences. The parenthetical enumeration of chat/contact fields (name_source, canonical_jid, phone_jid, lid_jid, phone_display) is heavier than needed for a reaction tool and could be trimmed against a shared contact description.

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?

No output schema exists, and the description compensates by documenting the return object's fields and the failure status, plus the recovery procedure for an unresolvable message. For a mutation-with-side-effects tool with a paywall gate, nothing an agent needs in order to call it correctly is missing.

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 baseline is 3, but the description adds real semantics: message_id must come from history/search and is not a reaction's own id, the other three params are recovery-only used when lookup fails, and "" removes the reaction. Slight redundancy with the schema's own emoji description keeps it from a 5.

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 ("Reacts to a WhatsApp message with an emoji") and immediately scopes where it applies: 1:1 or group, on the other person's messages or the user's own. The contrast with read_chat_history/search_messages (where the id comes from) makes it distinguishable from siblings without opening 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?

Explicit routing: take the id from read_chat_history or search_messages; chat, sender and from_me are resolved automatically. It names the fallback path ("If the message can't be found, the error asks for chat_jid ... pass them only then") and gives an exclusion (confirm with the user first because everyone sees it).

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

All WA MCP 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.