audit_domain_wcag_and_eaa

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

No annotations are supplied, so the description carries the full burden, and it omits the operational facts an agent needs: that `url` triggers a server-side fetch (timeouts, unreachable targets), whether `html` is size-limited, and whether results are truncated or gated without `proApiKey`. The mention of 'statutory fine risk estimation' hints at a computed output but never explains its basis or reliability. It does correctly imply a read-only audit, so it is not misleading, just thin.

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 with the verb, the input shape, the benchmark standards, and the differentiator (fine risk estimation) in that order. There is no filler and nothing a reader must scroll past to reach the operative 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?

With no output schema and no annotations, the description must stand in for a fair amount, and it does cover the audit target, the standards, and one headline output (fine risk). It leaves open what a report actually contains, how partial PRO results differ, and which of the two input modes to prefer, which matters for a four-parameter tool with all-optional fields.

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%, so all four parameters are already documented in the schema and a 3 is the baseline. The description reinforces the `standard` enum by naming both WCAG 2.2 AA and EN 301 549, and frames `url`/`html` as two input modes, but it never states that they are alternatives or what happens if both or neither are supplied. The `proApiKey` gating of 'complete violation diagnostics' is left entirely to the schema wording.

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 uses a specific verb (Audit) and resource (website URL or HTML string) and pins the scope to named standards (WCAG 2.2 AA, EN 301 549) plus 12 criteria. That is enough to separate it from siblings like audit_domain_ai_llms_readiness or scan_domain_cyber_hygiene without opening any schema. It stops short of an explicit sibling contrast, so a 4 rather than 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?

There is no guidance on when to choose this audit over the other audit tools, nor on when to pass `url` versus `html` for the same check. With zero required parameters, the schema alone permits an empty, useless call, and the description does nothing to prevent that. Usage is only inferable from the tool name and topic.

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