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

Goes well beyond the readOnly/destructive annotations: it discloses the deferred delivery model (the image appears in the NEXT task_state call), the redaction and masking behavior for sensitive fields and the Developer-mode exception, and warns that page content is untrusted website text rather than instructions. That is exactly the behavioral context an agent cannot get from annotations alone.

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 the delivery and safety details in short, information-dense sentences. The trailing 'Read-only.' duplicates the readOnlyHint annotation but is a single word and harmless.

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 tool with no output schema, the description correctly explains that results arrive via a subsequent task_state call rather than as a direct return. The remaining gap is mode semantics — an agent cannot tell from the description whether 'lite' or 'accessibility' is the right observation depth.

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?

With only 25% schema coverage the description does real work: it explains what 'screenshot' and 'combined' modes produce and where the image surfaces, and hints at the full-page scope. It leaves 'lite', 'accessibility' and 'dom' modes and the relevant-region scope unexplained, so it is strong but not complete.

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 ('Request a fresh observation of the task's current page') and enumerates the payload types it can return. 'Without acting on it' implicitly separates it from browser_run, though no sibling is named explicitly.

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?

Gives a clear condition for use — you want to look at the page without performing an action — and the sensitive_category parameter carries an explicit when-to-use rule ('only when the user's request needs that exact value'). It stops short of naming task_state or browser_run as the alternative when an observation already exists versus when you want to act.

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