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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered; the description adds real value beyond that by disclosing the returned private capability (audit_id + audit_key), revision 0, the retry-safe request_id, and the security scoping ('covers only this audit record, not access to the website').

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?

Front-loads the core action in the first clause, then layers return values, the no-persistence guarantee, and the capability's scope. Four tight clauses with essentially no filler, though the sentence packs several distinct facts that could be slightly easier to scan.

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?

An output schema exists, so return-shape detail is optional, yet the description usefully explains what the capability is and its limits. For a one-parameter, non-destructive bootstrap tool, an agent has everything needed to call it correctly; only explicit sequencing guidance toward the sibling save tool is missing.

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?

Only one parameter (url) and schema description coverage is 0%, so the description carries the burden: it names the URL as the target of the audit, matching the schema's uri format. It adds no format, validation, or normalization detail beyond that, which is adequate but minimal for a single obvious input.

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+resource ('Starts a new free audit session for a URL') and immediately clarifies what it is not: 'Saves nothing,' distinguishing it from read_audit/audit_site and the record_* siblings. An agent can tell this is the session-bootstrap step rather than an evidence-writing or reporting step.

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 description implies the ordering (begin an audit, then save evidence with the returned request_id), but it never names an alternative tool or states an explicit when-not condition. Usage is inferable from the surrounding narrative rather than stated.

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