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

Annotations already declare destructiveHint=true, and the description usefully scopes that destruction: only the proposal's pages are touched atomically, unaffected pages are preserved, nothing is published, and pages land editable in the normal editor. It does not address reversibility/undo or authentication needs, which would be needed for 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?

Three short sentences, front-loaded with the action and scope, then constraints, then resulting state. Every sentence contributes new information with no filler.

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?

The behavioral story (atomicity, staleness rejection, partial preservation, no publication) is well covered, which is the hard part for a destructive mutation. But with no output schema and zero parameter documentation, an agent still lacks guidance on requestId semantics, error conditions, and what the response contains.

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% across four required parameters, so the description carries the full burden. It only gestures at 'expectedProjectVersion' via 'Refuse les versions périmées' without naming it, and says nothing about requestId (presumably idempotency), projectId, or proposalId.

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?

States a specific verb and resource ('Appliquer une proposition choisie au brouillon du site') plus the destination (site draft), so an agent can distinguish it from request_site_proposal or submit_site_proposal. It does not explicitly name those siblings, so differentiation still requires inference from the names 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?

'sans publication' implies this is the pre-publish step and that publishing is handled elsewhere (e.g., publish_site_project), and 'Refuse les versions périmées' implies a freshness precondition. However, no alternative is named and no explicit when-not guidance is given, leaving routing to inference.

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