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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description adds genuinely non-obvious behavior: it refuses to run on a site that already has pages, it will not create a second site, and reusing the same requestId on retry prevents duplicate installations. It does not say what happens on failure (error vs. silent no-op) or whether the template install is reversible, which keeps it below 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?

The precondition and the 'does not create a second site' constraint are front-loaded, followed by idempotency guidance and then the post-install workflow. Every sentence carries distinct operational information with no repetition.

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 4-parameter mutation tool with no output schema, the description covers the precondition, idempotency contract, and the full follow-up path (customize → publish pages → activate site). The remaining gap is where to obtain a valid `templateId` and the exact failure mode when the site already has pages.

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 only 25% (only `home` is documented), so the description must compensate. It does explain the crucial idempotency semantics of `requestId` ('Réutiliser le même requestId lors d'une relance pour éviter les doublons'), which the schema does not. However, `templateId` — a required parameter — is never explained, and the description does not point to list_site_templates/list_website_templates as the source, nor does it clarify `name`.

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 object ('Installer un modèle dans le site unique du projet courant') and immediately bounds it with a precondition ('uniquement s'il ne contient aucune page'). It also explicitly negates a sibling behavior ('Ne crée pas de second site'), which separates it from create_website_from_template and clone_website in the sibling list.

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 an explicit when-to-use condition (site has no pages), a when-not path with an alternative for already-started sites ('utiliser sa conversation ou modifier ses pages'), and named follow-up tools (get_page/update_page, then publish each page, then activate the site). This is about as complete as routing guidance gets.

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