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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds that results are tied to *published* versions and that the output is a path/link intended for open_in_outil — helpful behavior beyond the annotations — but it says nothing about link lifetime, auth, or what happens for unpublished templates.

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 compact sentences with the outcome stated first and the next action second — nothing wasted. The trade-off is that the brevity is achieved through vagueness ("le path", "le modèle") rather than precision.

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 two-parameter tool with no output schema, the description should at least explain the shape of the returned links and how templateIds/device affect them. It instead leaves the primary input undocumented and only hints at the device dimension, so an agent cannot call it reliably without inspecting the schema.

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 full burden, and neither templateIds nor its 1–6 item limit is mentioned. The phrase "aux trois formats" faintly gestures at the device enum (desktop/tablet/mobile), but no explicit mapping to the device parameter or its default is given.

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?

"Liens d’aperçu des versions publiées" indicates it yields preview links for published template versions, which is more than a restatement of the name. However, it never explicitly names 'site templates' as the resource, and with siblings like list_site_templates, get_site_template_document, preview_components and show_preview, the description does little to make the distinction obvious.

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?

The second sentence gives a useful follow-up workflow: open the returned path with open_in_outil to inspect the template and its interactions. That is real usage context, but there is no statement of when to choose this over list_site_templates or get_site_template_document, and no exclusions or preconditions.

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