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

Annotations only say non-readOnly, idempotent, non-destructive; the description adds the substantive behavior: it returns CNAME + TXT records, SSL is auto-provisioned afterward, plan quotas (Free 1, Pro/MAX unlimited), the www/apex pairing and 301 redirect semantics, and named failure modes (domain_provider_error, invalid_hostname, path_not_supported, guidance.existingSite). One mild tension: it warns that connecting may 'replace that whole site' while destructiveHint=false — but this is domain-routing replacement surfaced through guidance.existingSite with a required user warning, not data deletion, so it does not rise to a contradiction.

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-loaded with purpose and return values, then organized as scannable bullets keyed to error codes and guidance fields. It is long for a 2-parameter tool and some clauses (redirect path/query preservation, 'as the text says') are detail-heavy, but nearly every line maps to a real decision the agent must make.

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?

There is no output schema, and the description compensates fully: it enumerates the returned records (CNAME, TXT) and the guidance fields (rootRedirect, rootNotServed, existingSite) with instructions for each. Combined with error-code handling and the verification follow-up, an agent has everything needed to call and interpret this tool.

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 coverage is 100%, so the baseline is 3; the description goes beyond it by explaining that a root such as example.com connects www.example.com and that the pair counts as one domain, plus the path_not_supported → set_site_url rule. It does not restate siteId semantics, but the schema already covers that adequately.

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 ('Connect the user's own domain ... to a Convika landing page') and immediately contrasts with the default {subdomain}.convika.page hosting. It also names the neighboring tools it is not (set_site_url for path-bearing values, get_domain_status for verification), so an agent can route correctly 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 explicit when-to-use ('use when the user wants their page on their own domain'), when-not/alternative routing ('a value with a path returns path_not_supported: call set_site_url instead'), and a follow-up step ('call get_domain_status after DNS setup'). It even includes negative guidance ('do not start a DNS-provider discussion during initial setup'), which is rare and useful.

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