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

Even with readOnlyHint/openWorldHint annotations, the description adds meaningful behavioral context: bypassing anti-bot systems, running steps in a real browser, and the steps schema discloses non-idempotency ('runs once and is not retried') and the 422 failure response with the offending step and page HTML. No contradiction with the annotations.

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?

The main description is four tight sentences, front-loaded with the core operation, then use case, output, and interaction workflow. The API link and selector-discovery tip are relevant, and there is no filler or repetition of the schema.

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 6-parameter tool with one nested object and no output schema, the description plus the schema covers the essential context: output ('raw HTML'), failure mode (422), selector discovery, and when to use it. It is slightly less complete because it never contrasts with fetch_parsed, and the main description leaves wait_method/wait_value usage to the schema.

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 description coverage is 100%, so the schema already documents every parameter, making 3 the baseline. The tool description adds a little context by framing steps as 'search, click, paginate' and pointing to list_elements, but it does not add meaning beyond the schema for wait_value, proxy_country, or sleep_seconds.

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 opens with a specific verb and resource: 'Fetch the fully rendered HTML of any web page' and adds the ScrapeUnblocker/anti-bot context. It says 'Returns raw HTML,' which hints at the difference from the sibling fetch_parsed, but it never explicitly names or contrasts that sibling, so the differentiation is left to inference.

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 gives an explicit trigger condition: 'Use when a normal fetch is blocked (403/429, captcha) or the page needs a real browser.' It also supplies a recommended workflow: use list_elements first to discover selectors before passing steps. It does not explicitly say when to prefer fetch_parsed, so full when-not guidance is missing.

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