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

Annotations already declare non-read-only, non-destructive, closed-world behavior, so the bar is lower, and the description still adds real value beyond them: it clarifies the page is created as a draft (not published), that 'Ne remplace jamais la page de départ' guarantees the source page is untouched, and that requestId is a stable key enabling safe retry without duplicates. What remains undisclosed is permission requirements and what happens on slug collision.

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?

Four compact sentences, front-loaded with the core action and scope, then the content-mode options, then the two safety/idempotency guarantees. Every sentence contributes; the only friction is the dense telegraphic phrasing ('Modèle facultatif (templateId), document natif (content) ou page vierge') which requires a second read.

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 six-parameter mutation with no output schema and no parameter descriptions, the description covers the essentials: destination context, content-source options, non-destructiveness, and idempotent retry. An agent could call it correctly; the missing pieces (return value, slug-conflict behavior, permissions) are secondary for this complexity level.

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 carry the semantic load, and it does for four of six parameters: fromPageId determines project/funnel context, templateId is explicitly optional, content is the native document payload, and requestId is explained as an idempotency key. Only name and slug receive no added meaning, which is a minor gap given their obviousness.

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+resource ('Ajouter une page brouillon') and pins down the scope precisely: the new page belongs to the same project/site and, where relevant, the same funnel as fromPageId. It is clearly distinct from a generic page-creation tool because of the draft/derived-from-page framing, though it never names the sibling 'create_page' it is closest to, so an agent must infer the distinction.

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?

Usage context is implied rather than stated: it tells you the tool clones context from fromPageId and offers three content modes (templateId, content, or blank), which helps an agent choose *how* to call it. However, there is no explicit when-to-use versus when-not guidance and no mention of the obvious sibling 'create_page' or 'create_site_from_template', leaving the tool-selection decision to inference.

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