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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered; the description adds real value on top by enumerating what the report contains and by disclosing that client-support notes derive from testing notes dated 2026-10 that 'may have drifted' and should be confirmed in Litmus/Email on Acid/seed accounts. That reliability caveat is exactly the kind of context annotations cannot carry. It stops short of a perfect score because it doesn't state the result format or whether findings are per-issue.

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 purpose is front-loaded in the first sentence, which is good, but the middle is one very long enumeration and the volatility of client notes is stated twice ('our notes describe them, and they drift' then 'may have drifted'), which is redundant padding in an otherwise short description.

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?

With no output schema, the description usefully compensates by listing the categories of findings the agent will receive, and the single required parameter is fully covered by the schema. The main residual gap is that it doesn't say how results are shaped (list of issues, severities, pass/fail) or whether checks are heuristic.

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?

There is a single parameter with 100% schema coverage ('The email HTML'), so the schema already does the work. 'Pass `html`' adds no syntax, size, or format detail (e.g. full document vs fragment, inline CSS required) beyond what the schema provides, so the 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 (check email HTML for dark-mode robustness) and immediately says to pass `html`, plus enumerates the concrete signals it reports (color-scheme declaration, prefers-color-scheme block, data-ogsc/ogsb hooks, hard-coded whites, low-contrast pairs, mid-tone text, background images). That is far more specific than a tautology, though it never names the adjacent siblings (check_colour_mode, dark_mode_palette, lint_email_html) to sharpen the boundary.

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 by 'Check how an email will fare in dark mode' and the closing advice to verify in real clients before sending, which is a workflow caveat rather than a when-to-use rule. There is no explicit statement of when to pick this over check_colour_mode, dark_mode_palette, or check_email_accessibility, so the agent must infer the routing.

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