kernel_audit_changes

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

With no annotations, the description carries the full behavioral burden. It does disclose ordering (newest first), the write-only filter, and that touched ids are returned, but says nothing about pagination, default window when 'since' is omitted, or how the 50 default limit truncates results — real risks for an audit tool.

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?

One dense sentence that front-loads the resource and scope, then ordering, then filter dimensions, then return content. No filler and nothing repeated from the schema.

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?

The return shape is covered by an output schema, and the description covers scope, ordering and filter dimensions adequately. For a 5-parameter audit tool with no annotations, however, the omission of time-window and result-cap semantics leaves meaningful gaps.

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?

At 40% schema coverage the description must compensate, and it does clarify the three dimensions (agent, run, tool) that map to actor_id, run_id and tool. It adds nothing for limit or since beyond the vague word "Recent", leaving half the parameters to a partly-documented schema.

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?

Names a specific resource (tool calls) with a precise scope qualifier ("that wrote something") plus ordering ("newest first"), so an agent can tell this is a write-audit feed rather than a general log. It does not explicitly contrast itself with kernels like kernel_audit_logs or kernel_audit_who_changed, so sibling differentiation is implied by scope rather than stated.

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?

Usage is implied by the write-only scope and recency, which tells an agent this is the place to look for recent mutations. There is no explicit when-to-use/when-not-to-use guidance and no named alternative for read-only or time-ranged auditing, so the agent must infer routing from sibling names.

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