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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantial context beyond them: no order is created, no payment is taken, the link embeds personal data in its fragment, it must not be published, and it supports only France and Belgium. This is exactly the privacy and transaction-boundary context an agent needs and that annotations cannot express.

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?

Short, front-loaded sentences that each add a distinct constraint: scope, non-action, consent, privacy, user confirmation, prohibited data, coverage country. No filler or restatement of the tool name.

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 and nested/partial-use parameters, the description does well on the behavioral side (privacy of the fragment, no payment, geographic scope) but leaves the return artifact underspecified — it never says where the link comes back or in what shape, and several input parameters remain uninterpreted. Complete enough to call safely, not complete enough to call confidently with non-default parameters.

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 6 parameters, so the description carries the full burden — yet it only adds meaning for client and consentement_coordonnees (optional, consent required). It says nothing about qte, src, fc_ref, or id_product, nor explains the meaning of the fc_ref pattern or the qte cap of 10, leaving four parameters undocumented in both schema and prose.

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 precise verb+resource: 'Prépare uniquement un lien privé vers FiltreCharbon.com', and immediately delimits it by what it does not do (no order, no payment). An agent can tell this is a link-generation tool rather than a catalog lookup, but the description never names or contrasts with the siblings details_filtre / trouver_filtre, so sibling differentiation is left implicit.

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?

Gives concrete usage conditions: client coordinates are optional, explicit user consent must be obtained before passing them, card data must never be submitted, and the link may only be shown to that user. This is strong when/when-not guidance, though it never routes the agent to an alternative tool for the catalog-discovery steps that presumably precede this call.

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