Skip to main content
Glama
discord-mcp

discord-mcp

by zongwei-tang

send_message

Sends text, replies, file or image uploads, stickers, and silent messages to Discord channels, threads, or DMs; use a user ID to open and message someone directly.

Instructions

Send a message to a channel, thread or DM — text, replies, file/image uploads (local path or URL), stickers, silent messages. Use user_id to DM someone.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "send_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
ttsNo
pollNoRaw poll object (or use create_poll)
filesNoFiles to attach (each: path, url or data_base64)
embedsNoEmbeds (bots/webhooks only)
silentNo@silent: send without notifications
contentNoMessage text (Markdown; mention users with <@id>, channels with <#id>, roles with <@&id>, custom emoji <:name:id>)
user_idNoOr: a user ID to DM (opens the DM for you)
reply_toNoMessage ID (or link) to reply to
channel_idNoChannel/thread/DM ID or a discord.com/channels/… link
componentsNoComponents (bots only)
sticker_idsNoUp to 3 sticker IDs
mention_replyNoPing the author of the replied message (default true)
suppress_embedsNoHide link previews
allowed_mentionsNo{parse:["users","roles","everyone"], users:[], roles:[], replied_user}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

The annotations already declare a non-read-only, open-world, non-destructive write, and the description adds useful capability context (attachments from local path or URL, stickers, silent sends, reply behavior via the schema). It omits behavior an agent would want for a write to an external service: permission requirements, rate limiting, whether embeds/components require a bot identity, and effect of an invalid attachment.

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?

One dense sentence covering target and payload types followed by a single short directive sentence for the DM case. No filler, no repetition, and the highest-value information (what can be sent) is front-loaded.

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?

For a 14-parameter, zero-required, nested-object write tool with no output schema, the description conveys the main modes but is thin on operational constraints — permission scope, rate limits, bot/webhook-only restrictions on embeds and components, and failure behavior go unstated. Annotations and high schema coverage carry much of the burden, keeping this at minimum-viable.

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 description coverage is 93%, so the schema already explains content markdown mentions, files, silent, reply_to, sticker_ids, and user_id. The description only restates a subset (attachments, silent, stickers, DM via user_id) without adding format or constraint detail beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ("Send a message to a channel, thread or DM") and enumerates the payload kinds it accepts (text, replies, file/image uploads, stickers, silent). It stops short of sibling differentiation: the DM path is described as "Use user_id to DM someone" even though a dedicated send_dm-style sibling exists, leaving the agent to guess which entry point to prefer.

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?

Implicitly frames usage by naming targets (channel, thread, DM) and giving one routing hint (user_id for DMs), which is enough to pick the right parameter. There is no explicit when-to-use vs when-not guidance, no mention of the sibling reply/DM tools, and no stated prerequisites such as channel permissions.

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