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

Annotations already flag destructiveHint and openWorldHint, and the description adds what they cannot: the lifespan (a minute or two), the asynchronous job model, and the exact way to detect completion or failure through get_site. It also discloses how pages are discovered (sitemap, falling back to the home page's links), which matters when a source has no sitemap.

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, the operation front-loaded and the polling instructions second. No filler; every clause carries operational meaning.

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 by explaining how results surface (the `job` field on get_site, or its error). For a two-parameter destructive background job, nothing an agent needs is missing.

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 still earns credit for clarifying that `source` drives link discovery and that the import preserves paths and copies images. It adds no formatting or edge-case guidance for `token`.

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 ('Replace the site's pages with an existing website's') and pins down the scope of the operation: word for word, same paths, images copied. That is clearly distinguishable from create_site or write_site, which build content rather than importing an existing site.

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 import scenario is unambiguous and the follow-up procedure is spelled out ('poll get_site until `job` is null, or read its error'). It never names the alternative tool for starting from scratch, so the agent must infer that create_site is the non-import path.

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