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

Beyond the destructiveHint annotation, the description discloses meaningful behavioral context: it can delete a source site, requires sites:delete permission in that case, requires all affected sites to be owned and delegated, and explicitly states it does not sign or change DNS records. This goes well beyond the annotations.

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 four concise sentences with no filler. The core action is front-loaded, and each subsequent sentence adds a distinct operational constraint or clarification 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?

The description covers prerequisites, safety confirmations, the moving/conflict case, the destructive deletion case, permission requirements, and the non-effect on DNS records. It does not describe the success response or error cases, but given no output schema and the mutation nature of the tool, the essential calling context is present.

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%, so the description must compensate. It clarifies confirmSite and confirmDomain as exact confirmation fields, explains expectedConflictSiteId as a reviewed value when moving a domain, and connects confirmDeleteSourceSiteId to the destructive source-site deletion path. The site and domain parameters are not individually explained but are obvious from the tool's purpose.

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 states a specific action ('Attach an already DNS-linked domain') with a clear resource and target, and distinguishes this from sibling tools like sites.unlink_domain or sites.preflight_domain by explicitly referencing preflight and domain attachment. The scope is unambiguous.

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 gives clear conditions for use: the domain must already be DNS-linked, preflight must have occurred, and the user must confirm the site and domain exactly. It also specifies when expectedConflictSiteId and confirmDeleteSourceSiteId are relevant, though it does not explicitly name alternative tools to use instead.

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