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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly declares 'read-only' (the safety profile) and discloses output ordering behavior: 'failures sorted by impact (biggest score wins first)'. It does not mention rate limits or behavior on unreachable/invalid URLs, a minor gap for a network-dependent audit tool.

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?

Three sentences, each earning its place: function, return contents plus sorting rationale, and usage sequencing. The core purpose is front-loaded and there is zero filler.

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 tool with no output schema and no annotations, the description covers the essentials: what it does, that it is safe (read-only), what it returns (passing/failing checks with impact-sorted failures), and the typical invocation sequence. Minor omissions are error handling for unreachable URLs and any rate-limit caveat, but nothing an agent needs to invoke it correctly 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?

The schema already covers the single url parameter at 100%, so the baseline is 3. The description adds a genuine semantic constraint beyond the schema by calling the URL 'public', signaling that internal or non-publicly-addressable URLs are out of scope. It also frames the operation as auditable content rather than just a URL string.

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 states a specific verb and resource: 'Run a read-only SEO / AI-discoverability audit on a public URL', and specifies the observable outcome ('Returns the passing and failing checks'). It also differentiates from the closest sibling by naming get_visibility_score as a predecessor, so an agent can tell this tool apart from a score-only tool without opening the schema.

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 final sentence gives explicit invocation context: 'Use after get_visibility_score to explain a low score', which tells the agent when this tool fits in a workflow. However, there is no when-not guidance or comparison against other audit-adjacent siblings like scan_domain or bulk_scan, so it stops short of a 5.

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