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

Annotations already declare the safe read profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description's added value is the sort order ('newest first') and the returned content ('status, compliance state, page counts and what each counted on audit.capture'). It does not disclose pagination or truncation behavior at the 50-item cap.

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 that packs scope, ordering, and return content without a wasted clause. Nothing repeated from the schema or annotations.

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 no output schema, the description usefully enumerates returned fields and the default ordering, which is the main thing an agent needs here. The gap is result-set sizing: no mention of default or maximum count despite a 50-item cap.

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 50%: site_id is documented inline, but limit carries only constraints (default 20, max 50) with no prose. The description reinforces the site-vs-organisation scoping but says nothing about limit or result-set sizing, so it does not fully compensate for the coverage gap.

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 ('Recent audits... for one site or the organisation') plus the ordering and the fields returned, so the agent knows this is a collection read rather than a single-record fetch. It does not explicitly name sibling tools like audit.audit.get or audit.audit.create, leaving the list-vs-get distinction implicit.

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?

'For one site or the organisation' implies the two usage modes, but the description never states when to prefer this over audit.audit.get or when the result set is truncated. Context is implied rather than spelled out, with no exclusions or alternatives named.

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