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

Annotations already declare readOnly, idempotent and closed-world, but the description adds material behavior beyond them: the address is POSTed and not stored or logged, the check is purely list-based with no DNS/MX lookup, and it shares keys and limits with the REST endpoint. These are exactly the operational facts an agent needs.

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-loads purpose, then layers caveats and privacy notes; each sentence carries information. The parenthetical enumeration is long but is the substantive content, not padding.

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?

An output schema exists so return values need not be explained, and the description still supplies the privacy, offline-accuracy and quota context an agent needs to call and interpret the tool correctly. Nothing material is missing.

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?

Only one parameter, and schema coverage is 100% with an example and max length already documented in the schema. The description adds no format or syntax guidance beyond what the schema provides, so 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 one email address') and then enumerates exactly what is tested: disposable list membership, role address, free webmail, look-alike domain, syntax, and typo suggestion. This clearly separates it from the sibling check_domain, which operates on a domain rather than an address.

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?

Gives strong context for interpreting results ('List-based and offline: no MX/DNS lookup, so a valid format does not mean the mailbox exists') and notes the shared engine/keys/limits with POST /v1/check. It never explicitly names check_domain as the alternative for domain-only checks, so routing between siblings is left implicit.

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