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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real value: no mailbox contact, no storage, and the exact set of checks performed. The only wrinkle is that a DNS mail-record lookup is arguably external interaction while openWorldHint is false, though that hint is more plausibly about not touching the user's world state, so this is a tension rather than a contradiction.

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?

Three tight sentences with the core action first, capabilities next, and caveats last; no filler and no repetition of the title or annotations.

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 does useful work by implying the result contents (flags, typo suggestion, mail-record findings) and by bounding its own reliability. The exact response shape is still left implicit, which is the only meaningful gap for a tool whose whole value is its structured output.

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 0%, and while the `email` parameter is self-evident, the optional `checkMx` boolean is never mentioned. Worse, "looks up the domain's mail records" reads as an unconditional behavior, which misrepresents a toggle that an agent may need to set or leave off.

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?

"Check an email address" is a specific verb+resource, and the following sentence enumerates exactly what the check covers (syntax including IDN, disposable/role/webmail flags, typo suggestions, mail-record lookup). An agent knows precisely what class of result to expect and can distinguish it from siblings like validate_phone or extract_emails.

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?

It clearly establishes the context of use (verify a single address before relying on it) and states an important limitation: it never contacts the mailbox, so it cannot confirm existence. It does not name an alternative tool or explicitly say when not to use it, so it falls short of a full when/when-not/alternative statement.

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