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

Goes well beyond the annotations by disclosing link lifetime (30 min), a hard rate limit (5 links/hour), that the merchant sees no payment data, and that no order is created — exactly the operational context readOnlyHint/openWorldHint cannot convey. No contradiction with idempotentHint=false, since each call yields a fresh link.

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?

Five short sentences, front-loaded with what is returned and how long it lasts, then the interaction model, then the limit. Every sentence carries a distinct fact; nothing is padding.

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 only two well-documented parameters, no output schema, and annotations covering the safety profile, the description fills the remaining gaps an agent needs: what comes back, its validity window, who pays, and the throughput cap.

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 already 100%, but the description adds real meaning: it explains the currency is forwarded to the site via ?wmc-currency= and that the XOF base price is always returned alongside. It does not name cart_id or spell out the currency enum's FR/EN variation, which lives in the schema.

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 concrete verb+resource: returns a payment link (valid 30 minutes) that opens the site's payment page for a given cart and currency. It also scopes what it does NOT do (no order created, no payment data seen), which separates it from the order/status siblings, though no sibling is named explicitly.

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?

'À donner au client. C'est le client qui paie lui-même' makes the usage context clear, and 'Le connecteur ne crée aucune commande' tells the agent not to expect an order afterwards. There is no explicit pointer to which sibling to use instead or when to prefer order_status, so it falls short of a 5.

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