neuron_a11y_audit

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

With no annotations provided, the description carries the full burden of behavioral disclosure and handles it well: it states exactly what the audit inspects and promises 'structured violations with severity and selectors.' It does not contradict any annotation. Remaining gaps are minor — it doesn't explicitly confirm a read-only side-effect profile or describe error behavior for an invalid tabId.

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?

A single front-loaded sentence: core action first, then the seven audited check categories, then the return shape. No filler, no restatement of the tool name, and every clause adds information an agent needs to invoke it correctly.

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 single-parameter tool with no output schema and no annotations, the description is largely complete: it covers what the tool does, what it checks, and what it returns (violations with severity and selectors). What's missing is any edge-case guidance (e.g., behavior when the page is unloaded or the tabId is stale), but the capability is adequately specified for reliable invocation.

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% — the single required tabId is already documented as 'Chrome tab ID to audit.' The description's phrase 'on a page' adds nothing beyond that. Since the schema fully carries parameter documentation, the baseline of 3 applies and the description neither improves nor degrades it.

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 opens with a specific verb-object pair, 'Run a WCAG accessibility audit on a page,' and enumerates concrete check categories (color contrast, alt text, form labels, heading structure, lang attribute, empty links, tabindex misuse). This clearly distinguishes it from siblings like neuron_seo_audit (SEO-focused) and neuron_audit_page (generic audit) without needing to open 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 use case is implied clearly: call this when a page's accessibility compliance against WCAG needs verification. However, it names no alternatives and gives no exclusions — notably, the sibling neuron_seo_audit is the obvious non-accessibility counterpart and is never referenced, nor are DOM-inspection tools like neuron_query_dom routed away from.

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