Kiểm tra dấu hiệu lỗi accessibility trên DOM thực tế

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

No annotations exist, so the description carries the full burden. It does add genuine behavioral context by disclosing the partial-coverage nature and the REVIEW_REQUIRED flagging convention, which tells an agent to expect possible false positives. It omits whether the audit is read-only, whether it needs a live browser session, and whether findings are persisted as artifacts.

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?

Two sentences, both front-loaded: the checklist of detected defects comes first and the caveat second. No filler or restatement of the title.

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 audit tool with no output schema and no annotations, the description covers what it detects and how results should be treated (partial, needs verification). The only real omission is a stated prerequisite for a running browser, which is a modest gap.

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?

There is a single required parameter, 'project', whose name is largely self-explanatory against the sibling project tools. The description adds nothing about it, but with one obvious parameter this is a minor gap rather than a blocking one.

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 gives a concrete verb (detect) and enumerates the exact defect classes: unlabeled inputs, unnamed buttons/links, images without alt, and skipped heading levels. That enumeration distinguishes it from tester_browser_layout_audit and tester_browser_security_audit by substance, even though no sibling is named.

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 states the check is partial and that flagged issues need model verification, which implies when output should be trusted versus re-examined. It never says when to run this instead of the layout or security audits, or what preconditions (e.g., an already-started browser session via tester_browser_start) must hold.

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