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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world behavior. The description adds genuinely useful async context: it returns a job id immediately and the build takes two to three minutes, with polling guidance. It does not cover auth, cost, or failure behavior, so it is strong but not complete.

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 tightly written sentences front-load the action and then the async return and follow-up timing. Every clause 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 job-creating tool with no output schema, the description explains the immediate job id return and the expected build duration plus polling path. The main gap is the undocumented state and industry parameters, which leaves the input contract incomplete.

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 names businessName, businessType, city, and services and clarifies 'up to three main services', but it omits the state and industry parameters entirely, leaving two of six inputs undocumented.

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 ('Starts building a preview website') and scopes it to a small service business with named inputs. It is clearly distinguishable from check_website_preview, which only checks status.

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 explicitly directs the agent to call check_website_preview with the returned job id about a minute later, establishing the correct follow-up workflow. It stops short of stating when not to use this tool or comparing against other siblings like get_plans_and_pricing.

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