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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds that the operation is asynchronous ('When the build is done'), which is genuinely useful, but says nothing about in-progress or failed states, polling cadence, or expiration of the job.

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?

Two sentences, no filler, with the core behavior front-loaded and the return values following. Slightly tight given it omits status semantics, but every sentence earns its place.

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 usefully enumerates what comes back on success, which is the key information for a one-parameter polling tool. Missing failure/pending state descriptions and job-expiry semantics keep it from being fully complete.

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 implies the jobId originates from start_website_preview but never names the 'jobId' parameter or states that the returned job identifier is what must be passed in. The linkage is inferable but not spelled out.

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 ('Returns the status of a preview') and explicitly ties the resource to its sibling 'start_website_preview', so the agent can distinguish this poller from the starter tool. It also names the concrete payload returned on completion (preview link plus account-save link).

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 phrase 'a preview started with start_website_preview' establishes the precondition and the correct ordering relative to that sibling. It stops short of explicit polling guidance (how often to re-check, when to stop) or any when-not-to-use exclusion, so it is clear context rather than a complete usage policy.

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