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

Goes well past the readOnlyHint/openWorldHint annotations with concrete disclosure: source is never rendered, run, stored or logged, and media-query rules are flattened while selectors are not matched to elements. That last point is exactly the kind of caveat an agent needs to avoid misreading results as a rendering check.

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 criteria and input format before the long flag list, and every clause is substantive. The enumeration of flagged patterns is dense but necessary for an agent to predict which findings come back.

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 steps in to describe the return value (DOM sequence of landmarks and headings, to be compared against visual order) and the analytical limits. Nothing an agent needs to invoke it or interpret the response is missing.

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% and there is only one parameter, so the schema already carries the baseline. The description still adds value by clarifying that inline styles are accepted alongside style blocks, which the schema summary omits.

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 ('Static check for WCAG 1.3.2 Meaningful Sequence and 2.4.3 Focus Order') plus the exact set of conditions it flags. An agent can distinguish it from neighbours like plan_focus_order or site_heading_outline 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?

The description makes the operating context explicit: pass pasted HTML or bare CSS, nothing is rendered, so it complements rather than replaces rendered audits. It never names a specific sibling as an alternative, which is why it falls short of a 5, but the when-to-use condition is unambiguous.

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