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

Annotations already cover the read-only, open-world, non-destructive profile, so the description is free to add the deeper behaviour, and it does: aria-hidden/hidden items are skipped because browsers omit them from the accessibility tree, and the count of skipped items is reported. It also discloses the markup-source limitation, which is exactly the kind of caveat an agent needs before trusting or explaining output.

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 purpose is front-loaded and the input contract appears early, before the long enumeration of detected patterns. The report list is dense but each item is a concrete check, and the closing limitation sentence is placed last where it is most useful. Slightly long, but every clause carries 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?

There is no output schema, so the description must describe returns, and its 'Reports:' enumeration does so in detail, including the reporting of skipped-item counts. Combined with the stated limitations and the two-input contract, an agent has everything it needs to call and interpret this tool.

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% and the two parameters are already documented, so the schema carries the load. The description only reinforces that the url must be public and that html is the alternative input, without adding syntax, precedence rules, or error behaviour beyond what the schema states. Baseline 3 is appropriate.

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 opening sentence gives a specific verb (finds) and a precise resource (repetition that makes a page harder to scan by ear), and the enumeration of checks that follows makes the scope unmistakably distinct from neighbouring tools like label_clarity_check or button_label_consistency. An agent can tell what this tool does and what it does not do without opening the 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?

It clearly establishes the context of use (accessibility audit of heading/link/landmark repetition) and specifies the exclusive input path: pass a public url or html. It also states an important when-not condition — CSS-hidden duplicates, shadow DOM and script-built content are not handled — so the agent knows when results will be incomplete. It stops short of naming an alternative sibling tool when that limitation applies.

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