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

Annotations already cover readOnly=false, destructive=true, idempotent=false and openWorld=false, but the description adds genuinely new behavioral context: partial-update semantics ('seuls les champs fournis changent'), the category-null removal rule, and the required write scope. This reconciles the destructiveHint (field overwrite, not deletion) rather than contradicting it.

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?

The two operating modes are front-loaded and the rest is compact and information-dense. The repeated min/max length constraints ('titre 1 à 140 caractères, texte 1 à 4000') are redundant with the schema and dilute an otherwise tight definition.

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?

With no output schema, the description carries the burden of explaining the response, and it says nothing about what is returned (e.g. the created template's id) or what happens on failure — a real gap for a create operation an agent may need to chain from. Parameter and behavioral coverage are otherwise solid for a 4-parameter tool.

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 100%, so the baseline is 3; the description exceeds it by explaining the placeholder syntax the body accepts ({prénom}, {ig_handle}, {date}, {stage_pipeline}), which appears nowhere in the schema. The length limits it restates duplicate the schema, adding no extra value.

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 and splits it precisely by mode: no template_id creates a model, with template_id modifies that model. This cleanly separates it from the read-only siblings list_templates and resolve_template without the agent needing to open 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 gives explicit conditions for each mode (absence/presence of template_id) and adds clear exclusions — 'Ne supprime jamais un modèle, n'envoie aucun' — which tell the agent this is not a delete or send tool. It stops short of routing to an alternative for deletion, so it is strong but not fully 5-level when/when-not/alternatives guidance.

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