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

Annotations already declare readOnlyHint/non-destructive, but the description adds real substance on top: nothing is rendered or run, nothing is stored or logged, and — importantly — listeners added by bundled libraries are invisible unless named. That limitation caveat is the kind of failure-mode disclosure that prevents a wrong conclusion from a clean scan. No return-format or severity detail, 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 standards it enforces, then the input contract, then the detection list, then the limits. The enumerated defect list is long and dense, but each item is specific and none is filler.

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?

For a one-parameter, annotation-covered, no-output-schema tool, this covers the essentials: what standard, what it detects, what to feed it, and — crucially — the static-only and library-blindness boundaries. An agent has enough to decide whether a clean result actually means compliant code.

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?

With a single required parameter at 100% schema description coverage, the baseline is 3. The description's 'HTML, CSS and any script you want covered' roughly mirrors the schema text 'HTML, CSS and script text to scan', adding only mild clarification that all three languages can be combined in one payload and that scope is caller-chosen.

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 description names a concrete technique ('Static scan') and enumerates the specific WCAG criteria (2.5.1, 2.5.2, 2.5.3, 2.5.4, 2.5.7, 2.5.8, 2.1.1, 1.4.13) plus the concrete defects detected, so the agent can distinguish it from neighbours like check_touch_targets or check_keyboard_shortcuts. It never names those overlapping siblings explicitly, which is what keeps it from a 5.

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 only 'how to use' content is the input instruction 'Pass `source` as HTML, CSS and any script you want covered.' There is no statement of when this tool should be chosen over check_touch_targets, check_keyboard_shortcuts, check_motion or audit_motion_css, and no exclusions, despite heavy topic overlap with those siblings.

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