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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description still adds real value by disclosing what is inspected and that results come back classified by severity, and by clarifying the target is the draft rather than the published site. It does not mention cost, timeout, or result-size characteristics of an audit run.

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 dense sentences with the subject, scope, checks, and return format front-loaded; nothing redundant or 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?

All four parameters are documented in the schema, annotations cover the safety profile, and the description states what the output contains despite no output schema. Minor gap: no indication of how large a violation report can get or whether partial results are possible.

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 the enum for level, the pageId default, and the id/templateSlug exclusion are already documented in the schema. The description adds only a light framing of the draft-vs-template choice, which the schema already states more precisely.

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+resource ("WCAG audit of a page") and enumerates the checks performed (contrast, alt text, headings, ARIA, interactive elements), plus the return shape ("violations by severity"). It does not explicitly name the sibling audit_seo as a different-in-kind alternative, so an agent must infer the distinction from naming alone.

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?

Usage is implied by "site's draft (or a stock template)", which tells the agent this runs against unpublished content or templates rather than a live site. However, there is no explicit when-to-use/when-not guidance, no mention of a prerequisite (e.g. site must be selected), and no routing to audit_seo for SEO concerns.

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