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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered, but the description adds meaningful behavior: the returned payload differs depending on whether the audit is still running or finished, and includeReport pulls a large report into structuredContent. It stops short of disclosing failure modes (e.g., unknown id) or polling expectations.

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?

Two sentences, zero filler, and the primary return contract is front-loaded before the optional-report hint. Every clause earns its place.

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 and a mutation-free read tool, the description carries the return-value burden well by describing both the in-progress and completed response shapes. The gap is maxFindings, whose paging/truncation semantics are explained nowhere.

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 67%: id and includeReport carry schema descriptions, while maxFindings is undocumented in both schema and description. The description reinforces includeReport's effect ('full report object with evidence'), which is slightly beyond the schema's wording, but adds nothing for maxFindings or 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?

States a specific verb and resource ('Returns an audit's status... or its grade, category scores and findings') and describes the output shape by run state, which clearly separates it from write tools like audit_site. It does not explicitly name a sibling such as list_audits, so differentiation is implicit via 'by id' 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?

The only usage guidance is conditional and parameter-scoped: 'Set includeReport to get the full report object with evidence.' There is no statement of when to prefer this over list_audits or audit_site, and no prerequisite or rate/auth context, so usage is implied rather than explicit.

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