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

The annotations already establish a safe, read-only operation, while the description usefully adds the covered event types and 12-month history limit. It does not disclose ordering, pagination behavior, default result size, or how filters interact.

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 compact sentence communicates the operation, representative scope, and retention window without filler. The concrete event list earns its place and avoids merely repeating the title.

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 five-parameter listing tool with no parameter documentation or output schema, the high-level event summary is insufficient for reliable invocation. Important gaps include kind values, cursor usage, filter semantics, result ordering, and the shape of returned events.

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?

The event categories indirectly hint at what kind might filter, but no accepted values or exact mapping are supplied. With 0% schema description coverage, the description also fails to explain limit, cursor, project_id, or actor_account_id.

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 states that the tool reads audit events, names representative event categories, and establishes a 12-month scope. It does not explicitly differentiate the tool from siblings such as list_activity or search_workspace.

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 security, key, spending, and operational event examples imply when an agent should consult the audit log. There is no explicit guidance about when to prefer list_activity or another tool, nor what to do for events outside the 12-month window.

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