Get audit log

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

The readOnlyHint annotation is consistent with the description of a historical record. The description adds context about the nature of the data ('who did what, to what, when, and why') and the contrast with live events, though it does not mention permissions or pagination behavior.

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?

Two sentences with no fluff. The first sentence defines the tool, the second gives usage guidance and filter examples. Information is front-loaded and every sentence earns its place.

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?

For a tool with no output schema, the description is complete: it explains what the audit log contains ('who did what, to what, when, and why'), when to use it, and how to filter. The schema handles parameter details and the annotation covers safety.

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 covers all 4 parameters with descriptions (100% coverage). The description adds semantic value by giving concrete filter examples ('action name like channel_create, member_ban_add, message_delete') and clarifying that user corresponds to 'acting user'.

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?

The description clearly identifies the tool as 'Discord's historical record of administrative actions' and states its purpose: 'Use this to investigate what already happened'. It also distinguishes from sibling subscribe_events by contrasting historical vs real-time activity.

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?

Explicit guidance is provided: 'for activity as it happens use subscribe_events' directly names the alternative. It also shows when to use this tool (investigate past events) and how to filter (by action or user).

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