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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the description carries a lighter burden but still adds substantial context: the analysis is static markup only, the detection list is fixed, and crucially it defines the meaning of a clean result — 'no known markup-level issue found,' not full compliance. This directly prevents the common misuse of treating a passing scan as a WCAG compliance certification.

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 sentences with zero waste. The first sentence front-loads the purpose and complete detection list; the second delivers the limitation and result interpretation. The enumerated failure list is long but earns its place because it tells the agent exactly what checks will run, which is actionable selection 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 one-parameter, read-only scanner, the description covers the key operational context: what it checks, what it can't check, and how to interpret results. The only gap is that no output format is described and no output schema exists, leaving the exact return structure (e.g., pass/fail vs. detailed findings) to inference. The enumerated check list and clean-result semantics cover most of what an agent needs.

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 the baseline is 3. The description still contributes meaning beyond the schema's 'full http:// or https:// URL' by constraining that URL to be 'live' and 'publicly reachable', which narrows what URLs are valid inputs. This is genuine added value but modest in extent.

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 ('Scan'), a tightly scoped resource ('a single live, publicly reachable web page's markup'), and enumerates the exact failure classes it targets (missing alt text, unlabeled form fields, missing lang attribute, empty links, skipped heading levels, missing page title, no h1, no skip link). The 'single page' and 'static markup analysis' qualifiers distinguish it from broader siblings like site-audit__audit_site_accessibility_and_agent_safety.

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 description communicates when to use the tool by stating the page must be live and publicly reachable, and explicitly says what it cannot do ('can't check color contrast, keyboard navigation, or screen reader behavior'), which functions as a when-not-to-use signal. However, it never names an explicit alternative tool for those broader checks, so it stops short of a 5.

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