Skip to main content
Glama
discord-mcp

discord-mcp

by zongwei-tang

create_thread

Creates a public or private thread in a Discord text channel, or starts a forum/media post with optional files, tags, and slowmode settings.

Instructions

Create a thread in a text channel, or a post in a forum/media channel (pass message: {content} and optional files for forum posts). type: 11 public, 12 private. [POST /channels/{channel_id}/threads]

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": {
      "channel_id": "<channel_id>",
      "name": "<name>"
    },
    "name": "create_thread"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesName
typeNoType
filesNoFiles to attach (each: path, url or data_base64)
messageNoForum/media post first message: {content, sticker_ids?, ...}
locationNolocation
invitableNoNon-moderators can add others (private threads)
channel_idYesChannel ID (text, voice, thread, forum or DM channel)
applied_tagsNoForum tag IDs to apply
rate_limit_per_userNoSlowmode in seconds (0-21600)
auto_archive_durationNoAuto-archive after inactivity, in minutes: 60, 1440, 4320 or 10080

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the basic safety profile is covered. The description adds meaningful behavior for the forum/media path (a first message with content is required, files are optional), but says nothing about permissions needed, whether the creator is auto-added to the thread, or what the response returns. Useful context, but not rich beyond the annotations.

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?

The definition is a single front-loaded sentence that leads with the primary action and nests the mode-specific details compactly. The trailing '[POST /channels/{channel_id}/threads]' endpoint is low-value for an agent that already has the schema. Dense but efficient, with no redundant restatement of the tool name.

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

Completeness4/5

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

For a 10-parameter creation tool with no output schema, the description covers the essential decision (text channel vs forum/media) and the ambiguous type values, while the schema carries the remaining parameter details. The main gap is the missing disambiguation from create_thread_from_message, an alternative that would matter to an agent choosing a tool.

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 would be 3, but the description adds meaning the schema lacks: the concrete values for the type parameter (11 public, 12 private), which the schema documents only as 'Type' with no enum. It also clarifies that message is the forum/media post first message paired with optional files. It does not touch auto_archive_duration, applied_tags, invitable, or rate_limit_per_user, but those are well documented in the schema.

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?

The description gives a specific verb+resource ('Create a thread') and splits it into two concrete modes: a thread in a text channel versus a post in a forum/media channel. A reader immediately knows the operation. It stops short of naming the sibling create_thread_from_message, so the boundary with that near-identical tool must be inferred from the phrase 'pass message: {content}'.

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?

It implicitly tells you which mode applies based on channel kind, and singles out that forum posts need a message object plus optional files, which is real usage guidance. However, it never states exclusions or alternatives — notably it does not say to use create_thread_from_message when the thread should start from an existing message, nor does it mention permission or channel-type preconditions.

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