confirmation_rdv

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

Annotations declare readOnlyHint=true, but the description describes a POST request that creates a confirmation document ('Confirmation de rendez-vous'), which is a write operation. This directly contradicts the read-only annotation, making the behavioral guidance misleading and unreliable.

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?

The description is compact: two sentences that efficiently convey the trigger condition, the resource, the context, and the HTTP endpoint. There is no filler, and every element carries useful information.

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?

The trigger condition and endpoint are present, and the schema thoroughly documents all parameters, so the mechanical calling information is largely covered. However, the direct contradiction between the read-only annotation and the POST creation operation creates a serious reliability gap that could lead an agent to misunderstand the tool's side effects.

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 100%, with detailed, purpose-driven descriptions for all 11 parameters. The description itself adds no parameter-level meaning, but the schema already fully documents each field, so the baseline of 3 is appropriate.

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 states the exact trigger condition ('QUAND un rendez-vous est pris et doit être confirmé par écrit') and clearly identifies the resource and action ('Confirmation de rendez-vous (app Agenda)'). Including the endpoint 'POST /api/v1/documents/confirmation-rdv' further pins down what the tool does, making it distinguishable from the many other document-generation siblings.

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 description provides an explicit 'when to use' condition via the QUAND clause, which tells an agent that this tool is for confirming already-made appointments in writing. However, it does not mention alternatives or exclusion cases, so it lacks explicit when-not-to-use guidance relative to sibling tools.

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