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

Annotations already carry the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds useful context beyond the annotations: the WCAG 2.2 edition, the fact that the analysis comes from the DOM, and the claimed output (violations with fixes). Notably, the wording 'static audit' is implied read-only, and that is not contradicted by the annotations but readOnlyHint=false warns the opposite; because the description never explicitly claims read-only, it is not a contradiction, though side-effect expectations stay fuzzy.

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 tight single sentence front-loads the verb and scope, then a compact checklist of 8 audit areas, and closes with the return value. There is no filler and no repetition of the input schema; every phrase adds 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?

For a two-parameter audit tool with a documented schema and an output schema, the description is nearly complete: it specifies the audit standard, the data source, the exact coverage, and the output type. It only omits a few meaningful details compared to an ideal spec, such as whether the entire domain is crawled or only a single page is audited, and whether any verification is needed before the run; these are left to the parameter description.

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%: target includes an example plus explicit ownership/authorization requirement, and lang comes with a complete enum and usage note. The description adds no parameter-level details beyond context, so the schema does the semantic heavy lifting; baseline 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: 'Static WCAG 2.2 accessibility audit' and enumerates the exact checks performed (image alt text, form labels, heading structure, landmarks, color-contrast signals, language attribute, duplicate ids, iframe titles). This cleanly distinguishes it from sibling audit tools (audit_seo, audit_performance, audit_security, etc.) without needing to inspect them.

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 applicability is implied: it is the accessibility-audit tool among the audit_ siblings, so an agent can infer when to pick it. However, the description never explicitly states when to use it instead of audit_full, or notes conditions such as needing an authenticated page to audit. Usage context is clear but not directly spelled out.

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