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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely useful context beyond that: static-only coverage limits, and the caveat that client-support notes dated 2026-10 may have drifted and must be confirmed in Litmus/Email on Acid/seed accounts. What it never discloses is the shape of the result — whether findings carry severity, counts, or locations — which matters because there is no output schema.

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?

Front-loaded with purpose and the required argument, then a compact check inventory, then limitations. Dense but every clause names a real check or a real constraint; the only mild cost is the run-on comma-separated enumeration, which is long but scannable.

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?

Since no output schema exists, the description must stand in for return values — and it does reasonably by listing the categories of findings, which is the right move. Gaps remain: nothing on how results are structured or prioritized, and no guidance distinguishing this from the highly similar email-accessibility siblings, which is the main thing an agent needs to call it in the right situation.

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?

With one fully documented parameter and 100% schema coverage, the baseline of 3 applies. The description says only "Pass `html`" and adds no meaning beyond the schema; it does not clarify whether a full document or fragment is expected, or whether styles must be inline in the markup versus in a `<style>` block — a distinction that materially changes the contrast and layout-table results.

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?

Opens with a specific verb and resource ("Check an email for accessibility basics") and enumerates the exact rule set it evaluates, so an agent knows precisely what will be inspected. It stops short of a 5 because it never differentiates itself from the near-identical sibling `audit_email_accessibility` (nor `lint_email_html`, `check_email_dark_mode`), leaving the agent unable to choose between them from the text 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?

Scope boundaries are implied by "Static checks only; it does not replace a screen reader pass" and the instruction to confirm in real clients, which tells the agent this is a triage step, not a final gate. However, there is no explicit when-to-use/when-not statement and no routing to the obvious alternative (`audit_email_accessibility`), which is the largest decision the agent actually faces here.

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