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

The description details the email confirmation flow, the 'only once' guarantee, the requirement for a user-supplied email, and the behavior when a registry is unreachable. This goes well beyond the annotations, which only note readOnly=false, openWorld=true, destructive=false.

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 description is substantial but every sentence provides essential operational detail, including edge cases and privacy. It is front-loaded with the core purpose and adds necessary nuance without redundancy.

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?

Given the tool's side effects (email, confirmation link, registry dependency), the description covers prerequisites, behavior under failure, and privacy. It does not describe the response payload, but this is acceptable for a tool whose primary outcome is an email notification.

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?

The input schema already provides descriptions for both domain and email. The description adds that the email must come from the conversation and that the address is stored only for this domain, adding practical meaning. This justifies a score above the baseline 3.

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?

The description opens with 'Register a watch on a domain that is currently taken, and be emailed once — and only once — when the registry confirms it has become registrable,' which clearly specifies the action and resource. It distinguishes from siblings like check_domains and whois by focusing on monitoring an unavailable domain rather than current status.

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 states 'Use when someone wants a name that is already owned, or asks to be told when one expires or drops,' providing direct usage guidance. It also clarifies that it is safe to call on unknown status because it creates nothing if free, but does not explicitly name alternative tools or when-not cases.

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