Skip to main content
Glama
discord-mcp-lite

discord-mcp-lite

read_messages

Read-only

Retrieve and paginate Discord channel or thread messages, newest first by default, with date or message-ID filters for browsing history. Read-only: no posting or deletion.

Instructions

Read channel or thread messages, newest first by default. Paginates past 100 up to 1000 per call. Works on thread ids too; forum channels must be read through their threads (list_threads first). Read-only: this server cannot post.

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": "read_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many messages to read, default 100.
sinceNoISO 8601 date; return only messages newer than this.
beforeNoMessage id (or ISO date) to start before; use the oldest id from a previous call to page back.
channel_idYesChannel or thread id.
oldest_firstNoReturn in chronological order, default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

readOnlyHint already declares a non-mutating operation, and the description reinforces the server-level constraint that it cannot post. Beyond annotations it adds real behavior: a 100-message default page, a 1000 hard ceiling per call, and the forum-channel read restriction. It does not discuss rate limits or failure modes for invalid ids.

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, front-loaded with what the tool returns and its default ordering, then paging limits, then the forum caveat and read-only note. No filler.

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 five-parameter read tool with full schema descriptions and no output schema, the description covers scope, pagination, ordering, and the forum constraint, which is most of what an agent needs. The ordering statement is wrong per the schema, which keeps it from being fully complete, and return shape is left implicit.

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

Parameters2/5

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 actively conflicts with the schema: it says results are "newest first by default" while the oldest_first parameter is documented as defaulting to true (chronological, oldest first). That is a direct ordering contradiction that could cause an agent to page backwards using the wrong end of a result set. The one useful addition is the tip about reusing the oldest id with `before`, though even that is muddled by the ordering conflict.

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?

"Read channel or thread messages" pairs a specific verb with a specific resource and states the default ordering and paging scope. It also separates itself from list_threads by explaining that forum channels must be read through their threads, so an agent can choose between them without opening schemas.

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

Usage Guidelines4/5

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

Gives a concrete routing rule: forum channels must go through list_threads first, and thread ids are acceptable input. It does not cover when to prefer list_channels/find_channel, but the primary usage distinction is stated explicitly.

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