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

Adds substantial behavior beyond the annotations: the call is non-destructive on its own ('NE FAIT RIEN TOUT DE SUITE'), it prepares a request, returns a tchin.tech URL where the user confirms with a Tchin PIN, and the request expires in 15 minutes. This explains the async confirmation flow that readOnlyHint/destructiveHint flags alone cannot convey.

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?

Compact and mostly front-loaded, with the critical no-op/confirmation caveat emphasized in capitals. Slightly better ordering would place the 'does nothing right away' warning before the deletion claim, but every sentence earns its place.

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, the description correctly supplies the return behavior (a tchin.tech confirmation address) and the time limit, plus the required next step. Nothing an agent needs in order to call this correctly and handle the result is missing.

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?

The single parameter has 100% schema description coverage ('Le nom ou le numéro de l'application'), so the schema already carries the semantics. The description adds no format, matching, or ambiguity-resolution details about the identifier beyond what the schema states; baseline 3 applies.

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 ('Supprime une application API') plus the concrete consequence ('ses clés ne marcheront plus'), which distinguishes it clearly from creer_application and mes_applications. An agent knows exactly what this tool accomplishes without opening the schema.

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?

Explains the applicable context (logged-in Tchin user, merchant or individual) and explicitly routes to the follow-up tool: 'Ensuite, appelez etat_demande.' It does not state any exclusion or alternative for deletion, but the workflow guidance is clear and actionable.

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