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

Goes well beyond the readOnlyHint/openWorldHint/destructiveHint annotations: it explicitly says this is a model of the browser rule derived from attributes, not a recording, that nothing is rendered or run, and that nothing is stored or logged. It also discloses that dialogs require manual testing and that names are 'guessed' — material caveats an agent cannot get from 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?

Front-loaded with the purpose and criteria, then the input, then the return contents, then the caveats — a sensible order with no filler. It is dense as a single long run-on with a comma list of findings, which is harder to scan than it needs to be.

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 takes on the job of describing returns and does it thoroughly: the numbered tab sequence, guessed names, excluded elements, and the full findings list. Combined with explicit non-execution and no-logging statements, an agent has everything needed to call it and interpret results.

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?

Only one parameter at 100% schema description coverage, so the schema already carries the burden and a 3 is the baseline. The description does add a small amount ('HTML with optional style blocks'), clarifying that <style> blocks are acceptable input, but adds no syntax or size guidance.

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 ('Models sequential keyboard navigation'), enumerates the exact WCAG criteria covered, names the input, and enumerates the output contents. An agent can distinguish this from check_keyboard_shortcuts or check_reading_order from the description alone.

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?

The description makes the usage context clear by naming the WCAG success criteria and the required `markup` input, so an agent can infer this is a static HTML focus-order audit. However, it never names an alternative sibling (e.g. check_keyboard_shortcuts, audit_form, check_reading_order) or states when NOT to use it, leaving routing to inference.

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