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

Beyond the readOnlyHint annotation, the description discloses the polling behavior, the meaning of keep_polling and preview_url, the self-refreshing progress card, and the special wait=false mode. These are behavioral facts not available from annotations alone.

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 compact, front-loads the trigger condition, and every sentence contributes a rule or constraint. There is no filler; even the progress-card sentence earns its place by explaining asynchronous UI behavior.

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?

For a polling tool with an output schema and read-only annotations, the description defines the full state-handling loop: when to poll again, when to send the preview URL, when to use wait=false, and when not to restart the build. Remaining details like exact status values are reasonably delegated to the output schema.

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?

The schema already documents token and wait with 100% coverage, so the baseline is 3. The description adds value by restricting wait=false to 'progress-card refresh' and emphasizing reuse of the same token, which are usage constraints not fully explicit in the schema.

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 title and description clearly identify a specific action: retrieving and acting on preview build status after start_build. The polling conditions and the explicit 'Do not start_build again' distinguish this tool from start_build and from the other sibling tools.

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 states the exact context ('Use this after start_build'), gives a concrete decision rule for when to poll again, and limits wait=false to progress-card refresh. It also explicitly tells the agent not to call start_build again, preventing a common mistake.

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