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

Annotations already declare readOnly/idempotent/non-destructive/open-world, so the safety profile is covered. The description still adds non-obvious behavior: a selector may be temporarily centered for capture and the original scroll position is restored before return, plus the stale/mismatched diff_from fallback to a full snapshot. It stops short of describing pagination or output size limits, so not 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?

Front-loaded with the use case, then workflow, then sibling comparison and the scroll caveat. Dense but every sentence carries distinct information; slightly long for a tool whose params are already fully documented.

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 an output schema present, rich annotations, and 100% schema coverage, the description only needs to supply selection/workflow guidance, which it does thoroughly, including the one side effect (temporary scroll adjustment) an agent would otherwise not anticipate.

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 baseline is 3, but the description adds operational meaning beyond the schema for diff_from (reuse the prior snapshot_id to get changed/removed nodes, stale input degrades safely) and the selector/include_screenshot pairing (center-and-report viewport bounds). Other params (device, endpoint, max_nodes) rely on 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 ('inspect a web page structurally through CDP accessibility'), and names the sibling it is not ('Prefer it over desktop ui_snapshot for page content'), so an agent can distinguish it from ui_snapshot and computer_snapshot without opening a 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?

Gives explicit when-to-use rules for the key optional params: reuse the last snapshot_id as diff_from after each step, fall back to a full snapshot when unavailable, and add include_screenshot=true only when final pixel/layout verification is needed. The alternative (desktop ui_snapshot) and the condition selecting it are spelled out.

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