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

Annotations already declare the write/non-idempotent/open-world profile, and the description adds genuinely new context: an authentication requirement ('connexion demandée la première fois') and the return behaviour ('Rend son adresse'), which matters because no output schema exists. It still omits what happens on failure or whether forms can be edited afterwards.

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 dense sentences, front-loaded with the actor and the core flow, then the return value, then the type list. The long type enumeration earns its space since it is the only source for those values, though the sentence is fairly breathless.

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 6-parameter mutation tool with no output schema and 33% schema coverage, the description covers the essential flow, auth and return value. It leaves the 'test' flag, the 'description' field, and the amount/quantity limits (100–100,000,000 XOF, 1–60 questions) unexplained, which leaves real gaps.

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%, and the critical gap — the nested 'type' field is a bare string with no enum — is fully compensated by the description enumerating all 19 question types. It also clarifies that 'montant' is a fixed price. It says nothing about 'test', 'titre' or 'description', which remain undocumented.

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 ('Crée un formulaire de paiement') and explains the full flow: the customer answers questions, then pays a fixed price. It does not, however, distinguish this from the close sibling 'creer_lien_paiement', which an agent could easily confuse it with.

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?

Usage is implied through concrete examples ('inscription, commande sur mesure, réservation…') and the target audience (marchand ou particulier connecté à son compte Tchin). There is no explicit statement about when to prefer this over a simple payment link, nor any exclusion or prerequisite beyond the first-time login note.

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