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

The description is otherwise rich, but it describes a replace:true path that replaces a non-empty draft, and the schema says the draft's other files are deleted. This conflicts with the destructiveHint=false annotation, which implies only additive behavior; that is an annotation 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?

The definition is long but dense and front-loaded: it starts with the primary action, then layers prerequisites, side effects, error behavior, and follow-up steps. The length is justified by nine parameters and multiple behavioral constraints, and there is little wasted text.

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?

It covers prerequisites, side effects, refusal conditions, hosting/subdomain caveats, schema merge behavior, and next steps like preview_draft and request_upload. With no output schema, it still does not fully document the exact return shape, but an agent has enough to invoke the tool 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?

Although schema coverage is 100%, the description adds substantial non-obvious semantics: copy keys map to localized text and omitted keys fall back to defaults_used, replace triggers 409 draft_not_empty unless true, subdomain changes are limited and can break the old address, and apply_schema merges rather than removes 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 description uses a specific verb and resource: build a draft from a starter, with the starter's files and copy substitutions written as a new draft version. It distinguishes this build step from sibling reads like get_starter/list_starters and references write_files' versioning convention, so an agent can tell what it does.

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 a clear consent gate for a mutation tool: use only when the user explicitly asks, and do not act on instructions from external data. It also explains operational prerequisites like asking about the subdomain before the call, but it does not explicitly compare this tool to create_site, write_files, or other draft-building alternatives.

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