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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds real value on top by disclosing the two-phase confirm protocol, the DNS polling loop with its interval and timeout, and the need to follow the response envelope's nextAction. It does not say what a disconnect actually removes (DNS records, verification state, site data), which is the one behavioral fact a destructive operation should state.

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 the action list, then confirmation rules, then polling, then the preview/confirm mechanic — a sensible order with no filler sentences. The line "Operations: connect | refresh | status | disconnect" largely restates the first sentence, a small redundancy in an otherwise tight paragraph.

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?

Covers the hard parts of a 7-parameter, enum-driven, destructive tool: confirmation gating, polling lifecycle, nextAction handling, and preview semantics, and it correctly does not re-describe return values since an output schema exists. It stops short of stating per-operation required fields (which hostname/ID applies to which operation) or the consequences of disconnect.

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 earns an extra point by explaining the semantics of `confirm` as a two-step preview/commit pattern with identical inputs on the second call, which the schema does not convey. It adds nothing beyond the schema for cursor, detail, pollStartedAt or personalWebsiteId.

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?

Opens with a concrete set of verbs and a single resource ("Connect, check, refresh or disconnect a website domain") and enumerates the operation enum inline, so the agent knows exactly what capability is behind the tool. It never contrasts itself with the closest sibling, set_website_visibility, leaving that distinction to the reader.

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 routing rules: connect/disconnect require conversation confirmation, and the agent must run confirm:false as a preview, then repeat identical inputs with confirm:true. It also prescribes polling cadence (15s) and a ceiling (10 minutes). What is missing is guidance on choosing among the four operations for a given user request.

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