discord-mcp

discord_read_messages

Read-onlyIdempotent

Fetch recent Discord channel or thread messages, newest first, with cursor pagination for older pages and Markdown/JSON output.

Instructions

Read recent messages from a channel or thread, newest first, with cursor pagination.

Needs the Message Content intent enabled for the bot or every message reads as empty.
Pass only one of before / after / around.

Returns: Markdown — each message as author, time, ID, text, attachments, reactions,
oldest at top; a footer gives the `before` cursor for the next page. JSON — envelope
{count, limit, has_more, next_before, items:[{id, channel_id, author{id, username,
display_name, bot}, content, timestamp, edited_timestamp, pinned, attachments?,
embeds?, reactions?, reply_to?, thread_id?}]}.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`after`	No	Only messages newer than this message ID.
`limit`	No	How many messages, newest first.
`around`	No	Messages surrounding this message ID.
`before`	No	Only messages older than this message ID — pass `next_before` from the previous page.
`channel_id`	Yes	Channel, thread, or DM channel ID.
`response_format`	No	'markdown' for reading, 'json' for full structured data.	markdown

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 3, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real operational context on top: a required bot intent whose absence silently yields empty content, cursor-based pagination semantics, and the mutually exclusive cursor constraint. This is exactly the kind of failure mode an agent needs warned about before calling.

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 the intent warning, then the cursor constraint, then returns. The return-format block is long and largely duplicated by the output schema, which is the one place it does not fully earn its space.

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?

With an output schema present and 100% parameter coverage, the description only needs to supply what structured fields cannot: the intent prerequisite, cursor pagination model, and cursor exclusivity. All three are present, so nothing an agent needs to call this 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 description coverage is 100%, so the baseline is 3. The description earns a bump by stating the one-of constraint across before/after/around, which the schema does not encode (no exclusiveMaximum/oneOf), and by tying `before` to the previous page's cursor.

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?

States a specific verb (read) and resource (messages) plus scope (a channel or thread, newest first, cursor-paginated), which implicitly separates it from discord_get_message (single ID) and discord_search_messages. It never names a sibling or an alternative, so the differentiation is inferred rather than explicit.

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 two concrete conditions: the Message Content intent must be enabled or reads come back empty, and only one of before/after/around may be passed. What is missing is routing guidance against the neighboring read tools (search_messages, get_message, list_pins).

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