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

The description discloses a real side effect the annotations do not: it 'Remplace et invalide le lien précédent', so an agent knows prior links stop working. It also flags that the response is sensitive and must not be published, implying the return value is a secret URL. It stops short of saying what exactly the response contains or whether the invalidated link can be recovered.

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 short clauses, zero filler, and the invalidation warning is front-loaded right after the action statement. Every phrase carries operational weight.

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 link-minting tool with no output schema and an undocumented parameter, the definition covers the important risks (previous link invalidated, response is secret) but omits the key unknown: what entity the id refers to and roughly what the response is. It is workable but leaves a real invocation ambiguity.

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% for the single required 'id' parameter, so the description carries the full burden — yet it says nothing about what the id identifies (a student? an enrollment? a site?). The generic name plus no description leaves the agent guessing at the argument's meaning.

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 verb 'Générer' plus the resource 'lien d’accès privé' makes the action clear, and the enrollment context comes through from the tool name/title. However, the description never distinguishes this from close siblings such as create_affiliate_access_link or create_community_member_access_link, which also mint private access links.

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?

'ne pas publier la réponse' gives one concrete handling rule for the invocation's output, which is more than nothing. It gives no guidance on when to choose this over the affiliate/community access-link siblings, nor any precondition for calling it (e.g., the student must exist first).

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