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

Annotations only cover the safety profile (read-only, idempotent, open-world). The description adds real behavioral context: what is verified, that up to five MX records are listed, and critically that the mail server is not contacted so a positive result does not prove the mailbox exists. That is exactly the kind of limitation an agent needs and cannot get from structured fields.

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?

Two tight sentences, front-loaded with the checks, then the caveat, then the access note. No filler sentences.

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?

For a single-param read-only tool with no output schema, the description covers inputs, checks performed, and the key limitation. It does not sketch the response shape (e.g. how syntax/domain booleans are returned), a minor gap.

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?

One parameter with 0% schema description coverage, but the single 'email' string is self-evident from the tool name and description. The description adds no format constraints (maxLength 320, minLength 1) beyond what the schema silently enforces.

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 and enumerates exactly what is checked: syntax, MX records, and address record. This clearly distinguishes it from siblings like validate_value or lookup_network.

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?

The description implies usage (call it directly, no auth needed) but never states when to prefer this over validate_value or lookup_network, nor when-not to use it. The 'no API key' note is access guidance rather than selection guidance.

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