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

The annotations already declare readOnlyHint, idempotentHint, and non-destructive status, so the safety burden is covered. The description still adds real behavioral context beyond that: it states the scope is limited to the homepage and warns that the call takes up to a minute.

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 short sentences, and the purpose and outputs are front-loaded ahead of the latency note and the input note. No sentence is filler, and each one adds distinct information.

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 read-only tool with no output schema, the description is nearly sufficient: it names all three return values and discloses latency. The only gap is the accepted address format, which is left for the caller to guess.

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?

There is only one parameter and the schema description coverage is 0%, so the description has to carry the parameter's meaning. 'Input is the website address' clarifies that it expects a web address rather than a business name, but it never specifies the format: whether it needs a scheme, whether it can include a path, or why the length is capped at 253.

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 gives a specific verb ('Audits') and resource ('an existing website's homepage') and spells out the three return values: health score, AI citation frequency, and top two fixes. It never names the sibling tools however, so an agent must infer that this is different from check_website_preview rather than being told so.

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?

It implies usage through 'existing website' and 'Input is the website address,' which hints this audits a live site rather than a preview, but it never explicitly states when to use this over check_website_preview or start_website_preview. There are no exclusions or prerequisites stated.

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