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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered elsewhere. The description adds real value beyond that by disclosing the response shape (tagAxes, tagFacets with counts) and that models keep their composition and editable sections, but it says nothing about pagination behavior or result ordering.

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 the returned fields, then the filtering capability. Nothing is redundant; the middle sentence on composition and editable sections earns its place as context for why one would pick a template.

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 read-only, 6-parameter list tool with no output schema, the description is largely adequate: it covers what is returned and how facets work. Two gaps remain — no differentiation from the several other template-listing siblings, and no explanation of the page parameter or of how tagAxes/tagFacets should drive a follow-up call.

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 coverage is only 33%, yet the description compensates by naming the filter concepts — keyword, métier, style, controlled-vocabulary tags — which map onto q, category, style and tags, and it points at the facet mechanism that explains the tag vocabulary. The AND/OR axis semantics come from the schema, not here, and the page parameter stays unexplained, so it is not a 5.

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 gives a specific verb and resource ('Parcourir la bibliothèque de modèles de sites') and even names the payload fields (nom, description, tags), so the agent knows exactly what it receives. It fails to distinguish this from close siblings such as list_website_templates, list_managed_templates or preview_site_templates, which is the only thing keeping it from a 5.

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 states that browsing can be narrowed 'par mot-clé, métier, style ou tags du vocabulaire contrôlé', which implies when to use it — when looking for a template to reuse. But it never says when to prefer preview_site_templates, get_site_template_document or list_website_templates instead, so the selection between near-identical siblings is left to inference.

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