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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety framing is covered. The description adds genuinely new behavior: output is drafts only (nothing published), the target project must be empty, and requestId makes the call idempotent. It does not say whether the operation is synchronous or returns a job handle, which would have earned a 5.

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 dense sentences with no filler, and the operation is front-loaded ahead of the constraints. The phrasing is terse to the point of being cryptic ('validés sous les règles courantes' is undefined), and the description is in French while tool names and sibling tools are English, which slightly raises parsing cost.

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 non-destructive write with three parameters and no output schema, the description covers preconditions, draft-only output, and idempotency reasonably well. It is still incomplete on return values (job id? created counts?), on what 'règles courantes' means, and on the undocumented 'name' parameter.

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 carries the burden. It explains requestId semantics as an idempotency key and implies that websiteId must reference an empty project, which is real added meaning. The 'name' parameter is never mentioned anywhere, leaving one of three parameters entirely 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 concrete verb and resource: install all pages and all layouts of a website, with the qualifier that the source inventory and documents must be validated. That is more specific than a tautology. It stops short of a 5 because it names no sibling, and this server contains near-identical names (create_site_from_template, create_site_project, clone_website, control_website_clone) that an agent cannot disambiguate from this text alone.

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?

Prerequisites are given ('inventaire source et les documents sont validés', 'projet vide'), which implies when the call is legitimate. However, there is no explicit when-to-use versus the obvious alternatives (create_site_from_template, clone_website, create_template_draft), so the agent must infer the routing decision from tool names alone.

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