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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context: it models Chromium's accessibility tree rather than recording specific screen readers, it reports bot-protection interstitials as void rather than clean, and it explains the challengeSuspected fallback when the title contradicts the read tree. These details go well beyond the annotations and help an agent interpret results correctly.

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?

The description is dense but well-organized, front-loading the primary use case and then layering caveats. Every sentence earns its place, but it is long and somewhat technical; a slightly more compact phrasing could improve scannability. The structural separation of the key distinction (rule checks vs sense read-aloud) is effective.

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?

Given the tool's complexity — multiple modes, output variations, void/interstitial handling, and the cognitive model of how screen readers linearize content — the description is remarkably complete. It covers what the tool returns, what it does not (exact phrasing ground truth), how to interpret void runs, and when to enable includeNodes. No output schema exists, so the description appropriately carries the burden of explaining return behavior and does so thoroughly.

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, but the description adds meaningful context for the mode parameter ('reading' vs 'rotor' vs 'both') and the includeNodes parameter (structural findings are always included, nodeIds capped to 5 examples). It also clarifies that maxNodes truncation is always reported. However, it doesn't add much beyond the schema for url/website, and the description doesn't explain the default homepage behavior for url — though that is in the schema.

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 starts with a specific, actionable use case — determining whether a page makes sense read aloud — and contrasts it with rule-checking, which distinguishes this tool from sibling tools like check_page_alt_text and list_violations. It also clearly names the resource (screen-reader transcript) and what it produces (announcements in order, roles, names, states and hints).

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 explicitly states when to use this tool ('when the question is whether the page still makes SENSE read aloud') and when not to rely on it ('do not treat the exact phrasing as ground truth' because it models Chromium's accessibility tree, not NVDA/JAWS/VoiceOver recordings). It also explains that stored scans don't hold this data, so no alternative tool can substitute, and it names the read-only nature.

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