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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value by naming what is destroyed ('retained inputs and results') and the tenant ownership constraint, but is silent on whether the audit record itself survives, whether deletion is recoverable, or what happens on a non-owned audit.

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 front-loaded sentence with no filler; the ownership constraint comes after the destructive action so the agent reads the risk first.

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 one-parameter destructive tool with rich annotations and no output schema, the description covers target and scope adequately. Minor gaps about post-deletion state of the audit record remain, but nothing blocks correct invocation.

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?

There is one parameter with 0% schema description coverage; the schema only supplies a 32-hex pattern. The description identifies the audit as the deletion target, which maps to audit_id, but adds no format or identity details beyond that implicit link.

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 and resource ('Delete retained inputs and results for an audit') plus scope ('owned by this tenant'). It is clearly distinct from delete_upload, though it does not explicitly name that sibling as the alternative.

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 tenant-ownership clause implies context (only audits this tenant owns can be deleted), but there is no guidance on when to use this rather than delete_upload, or on preconditions such as audit state or whether results must be retrieved first.

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