Skip to main content
Glama
Sign In
Blujay MCP Server

Blujay MCP Server

Official
by blujayhq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

React to a message

react_to_message

Add or remove a tapback or single-emoji reaction on an iMessage; a new reaction replaces your previous one so recipients see your updated response.

Instructions

Add or remove a reaction on an iMessage: a tapback (love, like, dislike, laugh, emphasize, question) or any single emoji. One reaction per person per message: a new one replaces yours. The person sees it.

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>"
    },
    "name": "react_to_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
emojiNoExactly one emoji, such as 😍 or 👍🏽, instead of a tapback. People on iOS 17 or earlier see it as a text.
removeNo
reactionNoA tapback. Pass this or emoji.
message_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only tell the agent this write is non-read-only, non-destructive, non-idempotent and open-world; the description adds material facts beyond that: a new reaction replaces your existing one, and the recipient sees it. It does not cover failure modes (e.g., removing a reaction you never added) or what the call returns, which is the main remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, all doing work: first defines the action and its two modes, second states the replacement rule, third states visibility. The key constraint (one reaction per person, new replaces old) is front-loaded with no filler.

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

Completeness3/5

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

Given four parameters, no output schema, and no annotations about return behavior, the description covers the reaction model well but leaves the remove flag's interaction with reaction/emoji ambiguous and gives no guidance on identifying the message. An agent could still call it, but may guess wrong on removal semantics.

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

Parameters3/5

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

Schema coverage is 50%: emoji and reaction are documented in the schema, while message_id and the remove flag are not. The description's 'add or remove' implies what remove does and it reiterates the tapback set, but it never explains message_id's expected format or whether remove must be combined with reaction/emoji to target a specific removal.

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 pair ('add or remove') and resource ('a reaction on an iMessage'), then enumerates the two reaction families (tapback values, single emoji). This is clearly distinguishable from siblings like send_message or edit_message, which manipulate message content rather than reactions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the domain ('one reaction per person per message'), but the description never states when to prefer this over send_message for a short reply, nor any prerequisite such as needing a valid message_id from get_message. No exclusions or named alternatives are given, so an agent must infer the boundaries.

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

Deploy Server

Other Tools