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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description layers on substantial extra context: the exact checks performed, the ~40 and ~110-140 character thresholds, estimate/client dependency, and the honesty that testing notes dated 2026-10 may have drifted.

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 the purpose, then inputs, then enumerated checks, then caveats — no wasted sentences, though the dense parenthetical thresholds and the long caveat clause make it heavier than strictly necessary.

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 and full parameter documentation, the description supplies everything an agent needs: what is checked, how inputs are chosen, and the reliability caveat — nothing material is missing for correct invocation.

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 coverage is 100%, so the baseline is 3; the description earns above baseline by explaining that only the first hidden block at the top of the body is read and that `subject` is used for the repeat comparison, adding meaning the schema lines don't convey.

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?

Specific verb and resource ('Check a preheader') with an immediate plain-language gloss ('the preview text after the subject in the inbox') that cleanly separates it from siblings like check_email_subject or lint_email_html.

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?

Explicitly explains the two input modes (pass `html` or `preheader` directly, plus optional `subject`) and cautions to confirm in real clients before sending. It doesn't explicitly route the agent away from adjacent tools such as check_email_subject, so it stops short of full alternative guidance.

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