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

Annotations already establish a safe read-only, closed-world profile, and the description adds substantial context on top: a detailed inventory of the checks performed and, crucially, three explicit blind spots (no rendering, no <style> class resolution for colour, no plain-text confirmation). That is exactly the behavioural disclosure an agent needs to trust and interpret the output.

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, then the check inventory, then caveats, then output shape — a sensible order. The middle enumeration is long but each item is a genuine distinct capability rather than padding, so it earns its space despite a slight density cost.

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?

There is no output schema, and the description compensates by stating what a finding contains ("names the WCAG criterion and a fix"). Combined with the documented limitations, an agent has enough to decide whether to call it and how to read the results.

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 parameter and 100% schema coverage, the schema already carries the load, but the description adds a meaningful qualifier — "the full source" — signalling that fragments will not work and that the caller must inline styles rather than pass a URL or file reference. Modest but real value beyond 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?

Names a specific verb and resource ("Accessibility audit of marketing or transactional email HTML") and enumerates the concrete defect classes it detects, so the agent knows exactly what comes back. It does not differentiate itself from near-siblings such as check_email_accessibility, lint_email_html, or check_email_dark_mode, which is the main missing piece.

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 through the limitation list — "does not render the email, resolve <style> classes for color, or confirm a plain-text alternative" tells the agent when results will be incomplete. That is genuine scoping guidance, but it never names an alternative tool or a condition that would send the agent to a sibling instead.

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