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

With annotations declaring readOnlyHint=false and destructiveHint=false, the bar is lower, and the description still adds real value: it discloses the authentication prerequisite and, critically, that only the public key is returned while the secret key must be retrieved on Tchin's API page with the Tchin PIN. It does not note that repeated calls produce separate applications, despite idempotentHint=false.

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 compact sentences that front-load eligibility, then the action, then the return behavior. No filler, though the parenthetical about first-time connection is slightly buried and the key-handling clause is dense.

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?

There is no output schema, and the description usefully covers what comes back (public key) and how to obtain the secret key, so return semantics are handled. The significant remaining hole is the six undocumented input parameters, which for a creation tool with an enum and five booleans is a real gap.

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 must carry the burden of parameter meaning and it does not: 'nom', 'crypto', 'description', 'compte_tchin', 'mobile_money' and the 'frais_paiement' enum (client vs marchand) are never mentioned. An agent must guess what each flag toggles on the created application.

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 specific verb and resource ('Crée une application API') plus the business purpose ('pour encaisser depuis un site ou un appli'), which lets an agent distinguish it from mes_applications (listing) and supprimer_application (deletion) without opening schemas. It stops short of naming a sibling 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?

The audience prerequisite is stated ('utilisateur connecté à son compte Tchin, marchand ou particulier') and a use case is implied ('pour encaisser depuis un site ou un appli'). However, there is no guidance on when to prefer this over siblings like creer_lien_paiement or creer_formulaire for taking payments, and no stated exclusions.

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