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

Annotations already cover read-only, idempotent and open-world safety. The description adds real behavior beyond them: visible-only filtering by default, refs that survive markup shifts and address live elements, and disclosure that disabled/checked/expanded state and current field values are marked. Cross-platform scope (iOS Safari and Android Chrome) is also stated. No rate-limit or size-ceiling behavior is mentioned, keeping it from a 5.

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 most important instruction ('START HERE before acting') is front-loaded and the ref format is shown inline as a concrete example. It is one dense paragraph with a couple of near-redundant clauses about refs, but nearly every sentence carries actionable 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?

With no output schema, the description carries the burden of describing the return value, and it does: the `role "name" [ref=eN]` line format, the visible-by-default rule, and the state/field-value markers. Combined with 100% schema coverage on the 8 parameters, an agent has everything needed to call and interpret it.

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 coverage is 100%, so the baseline is 3, but the description adds usage-level meaning the schema lacks: it explains what interactiveOnly actually filters to ('just the things you can act on') and frames selector as a scoping mechanism for large pages. The remaining six parameters are left to the schema.

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 ('read the page as a structured tree of what is on it') and immediately differentiates itself from siblings like webpage_get_dom by explaining the ref-based addressing model. An agent can tell what this produces and why it differs from raw DOM tools without opening any 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?

'START HERE before acting' is an explicit sequencing directive, and it names the downstream tools (webpage_click / webpage_type / webpage_hover) that consume its refs. It also gives the conditions for its two narrowing options (interactiveOnly for actionable-only, selector for large pages). It stops short of stating when NOT to use it versus web_snapshot or webpage_get_dom, so not a full 5.

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