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 write-but-non-destructive profile is covered. The description adds genuinely new behavior: the page is created as a draft ("brouillon") and requires no file, build or deployment step, which tells the agent this is a data-only mutation whose output is not yet live. It stops short of stating auth/permission requirements or whether a subsequent publish_page is mandatory to go live.

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?

Purpose is front-loaded in the first sentence and each subsequent sentence adds a distinct fact (no build/deploy, composition routes, template optionality). It is dense but not padded; the only mild redundancy is the final two sentences both circling the optional-template point.

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 8-parameter creation tool with no output schema and near-empty schema descriptions, the description covers the composition decision well but leaves the identity/scoping parameters and the return value unaddressed. An agent still cannot tell from the definition what siteId or funnelId do when omitted, or what identifier comes back.

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 13% (just templateId), so the description has to compensate and it does so partially: it explains templateId's source, template's skeleton semantics, and that content is the native free-form route. However, five of eight parameters (name, slug, siteId, funnelId, kind) get no meaning at all beyond their types, and the enum relationships between kind and template are left implicit.

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?

"Créer une page brouillon en base" names a specific verb (create), a specific resource (page) and the resulting state (draft, in the database). The following sentences name the sibling tools this replaces for each composition route (compose_page, import_html_page, list_site_templates), so an agent can distinguish it from create_editor_page, create_payment_page or create_website_from_template without opening any schema.

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 enumerates the four ways to populate the page (native content, compose_page sections/elements, import_html_page converted HTML, templateId from list_site_templates), which is exactly the when-to-use-which routing an agent needs. It also resolves the ambiguity between the two template parameters: templateId pulls a library template installed server-side, while template alone yields a minimal skeleton to be completed before delivery.

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