Read messages from a Discord channel to access conversation history. Specify the channel ID and optionally limit the number of messages returned.
Read messages from a Discord channel.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| before | No | ||
| bot_token | No | Bot token. Optional when connected in UnClick or the documented env var is set. | |
| channel_id | Yes |
Changes observed during successful MCP inspections.
v0.1.11Input schema / properties / bot_token / descriptionAdded value: +"Bot token. Optional when connected in UnClick or the documented env var is set."Input schema / requiredPrevious value: -[
- "bot_token",
- "channel_id"
-]New value: +[
+ "channel_id"
+]v0.1.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered by structured data. Beyond the one-line purpose, the description adds nothing: no pagination behavior, no mention that a bot token may be required, no scope/permission context for reading a channel.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with zero redundancy and a clear front-loaded verb, but it is terse to the point of under-specification rather than genuinely concise. There is no structural content beyond the purpose statement.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With four parameters, no output schema, and a third of the schema undocumented, the description should carry more weight. It leaves pagination semantics, authentication, and return shape entirely unstated, which is insufficient for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 25% — only bot_token carries a description in the schema. The description says nothing about channel_id format, what 'before' means (pagination cursor?), or what 'limit' defaults to or caps at, so it does not compensate for the low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (read) and resource (messages in a Discord channel), which distinguishes it from discord_send and discord_react. It does not, however, differentiate itself from the closely related discord_search or discord_thread siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no guidance on when to use this versus discord_search or discord_thread, and no prerequisites or exclusion criteria are stated. An agent must infer the retrieval-versus-search distinction from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.