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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description earns credit for characterizing the payload's shape (aggregate error-free count, per-problem page frequency plus rationale, delta vs. previous audit). It does not mention that results depend on a prior audit existing or how paging behaves, which are the remaining behavioral gaps.

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 sentence, no filler, and the core deliverable is front-loaded before the enumeration of sub-results. Every clause maps to a distinct piece of returned content.

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 an output schema present the description needn't explain return values in detail, and annotations cover safety; two optional params are fully documented in schema. What is missing is the routing context — given five audit/change-adjacent siblings, an agent cannot tell from this text alone which one to reach for.

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 100% and the schema descriptions are unusually good — the optional 'site' parameter's fallback-to-list behavior and the 'cursor' pagination contract are fully spelled out. The description adds nothing about either parameter, so the baseline 3 applies.

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 names the resource precisely (page-by-page site audit) and enumerates what the caller receives: pages without errors as k of n, per-problem page counts with rationale, and the delta since the prior audit. It is clear what the tool yields, but it never distinguishes itself from the crowded sibling set (get_site_check, run_site_check, scan_site, get_what_changed), which overlap heavily with the 'what changed since the previous audit' framing.

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?

There is no statement of when to call this versus get_site_check, run_site_check, scan_site, or get_what_changed, nor whether a prior audit must exist for the delta to be meaningful. The agent must infer the selection criteria from names alone.

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