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

Annotations already mark it as a non-read-only, open-world, destructive operation. The description adds key behavioral context beyond that: it runs asynchronously in the background, costs organisation credits, and returns a siteId for progress polling via get_site. It does not explain why destructiveHint is true, but there is no 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?

Three tight sentences with no filler, front-loaded with the core action and then the operational details and next step. 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?

For an async, credit-billed creation tool with no output schema, the description supplies the essential operational facts: background execution, billing impact, and how to track progress. It could mention error behavior or permissions, but it covers what an agent needs to invoke and follow up correctly.

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%, so the schema already documents all four parameters. The description does not add format, ordering, or constraint details, and the phrase 'from a description' could momentarily blur the distinction between the prompt and description fields. Baseline 3 is appropriate.

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 description states a specific verb and resource ('Start building a new site') and frames it against a sibling ('the same as asking Zenning in chat'), so an agent can tell it apart from ask_zenning and edit_site without opening either 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?

It gives clear context for when to use this tool (to create a site from a prompt) and explicitly names the follow-up tool get_site for checking progress. It does not list exclusions or alternatives in a when-not sense, but the Zenning comparison helps.

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