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

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false, openWorld=false) by disclosing the pending initial state, the two DNS records the caller must act on, the exact activation condition, the billing prerequisite, the capability requirement, and that it proxies the SHIP API. That is precisely the auth, lifecycle and side-effect context 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?

Four front-loaded sentences that each carry information: action, lifecycle, activation condition, prerequisites. The API-doc pointer and capability sentence are slightly boilerplate but still useful for an agent that needs to scope permissions.

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 correctly compensates by explaining that the response contains a TXT and a CNAME record. It is nearly complete for a mutation tool; only failure modes (domain already taken, wrong plan tier) and the hand-off to verification are unstated.

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 100% and both parameters are self-documenting ('Site id from list_sites', 'blog.example.com' example), so the baseline of 3 applies. The description adds nothing about hostname constraints (max 300 chars, uniqueness, apex vs subdomain handling) that the schema doesn't already say.

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 ('Add a custom domain to a hosted site') and immediately distinguishes itself from the read/remove siblings by describing the pending-state creation flow and the DNS records returned. An agent can tell this apart from list_site_domains, remove_site_domain and verify_site_domain without opening any schema.

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 concrete preconditions for use: 'Needs a paid plan' and 'Requires the config:write capability', plus the implied follow-up that the domain only goes live once the TXT record is found and the certificate is active. It stops short of explicitly naming verify_site_domain as the next step or stating when not to call it (e.g. hostname already registered).

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