Audit accessibility (WCAG 2.2 / European Accessibility Act)

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

Annotations already declare readOnly/openWorld/non-destructive/non-idempotent, and the description layers substantial additional context on top: execution happens in a real headless browser, results can come back asynchronously as 'running' with a runId, and there is a billing/auth model (caller's own APIFY_TOKEN, Apify pay-per-event, nothing charged by this server). It also discloses the tool's accuracy limitation, which an agent needs in order to interpret results responsibly.

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?

Four sentences, front-loaded with the action and then descending into output, limitations, and billing/auth. Each sentence carries distinct, non-redundant information and nothing repeats the schema or annotations.

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 an output schema present, the description needn't enumerate return fields, and it still summarizes them (score, impact counts, pages, code-level fixes, report link). Combined with disclosed auth/billing, async behavior, and scope limits, an agent has everything needed to call this correctly and interpret the result.

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%, so every parameter including the enum on wcagLevel and the spend cap is already documented in structured form. The description adds no parameter-level detail beyond the schema (e.g. it never explains maxPages or maxCostUsd trade-offs), so the baseline of 3 applies.

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 ('Crawls pages in a real browser and runs axe-core WCAG 2.2 checks'), names the conformance standards (WCAG 2.2 A/AA/AAA, EN 301 549, EAA) and what it returns. This is clearly distinguishable from siblings like full_website_audit or scan_speed_and_revenue, which address different audit dimensions.

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 context (accessibility/legal compliance auditing) is implied strongly, and there is a useful caveat that automated testing covers only a subset of WCAG issues and does not replace a manual audit. However, no sibling alternatives are named and no explicit when-to-use/when-not routing is given, e.g. versus full_website_audit or when to follow up with get_audit_results (only the schema hints at that).

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