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

Goes well past the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing that only PREPAID rates can be booked through an agent, that the stay is charged in full at booking time and is non-refundable, and that a clear error is returned when the hotel is full or closed. The non-refundable payment consequence is exactly the kind of high-stakes behavior an agent must know before calling.

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?

Front-loads purpose, then the simplest call shape, then return values, then the critical prepaid-only constraint. Every sentence carries content, though the UCP short-form/variant explanation adds some density relative to the tool's core purpose.

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 covers returns (available room and rate, total price in euro cents, finalization URL) and covers the mutation/error behavior. It leaves minor gaps around what happens to an existing session on repeat calls and any auth requirements, but is otherwise complete for a 5-param nested-payload tool.

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 80% and the description still adds value: it recommends the short form (check_in, check_out, adults) and explicitly notes that the nested UCP booking.stays[] shape is an accepted alternative, clarifying the relationship between the flat and nested parameters. It does not add syntax detail for the booking.booker/property sub-objects.

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 ('Ouvre une session de réservation') and pins it to a concrete property (Hôtel-Rooftop Les Voiles, Toulon/Mourillon) with named inputs and outputs. An agent can tell this apart from create_rooftop_reservation/get_booking_session, though it never explicitly names those siblings to reinforce the boundary.

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?

Gives practical invocation guidance (short form check_in/check_out/adults is easiest; UCP booking.stays[] also accepted), which implies how to call it. However it never states when to prefer this over create_rooftop_reservation or update_booking_session, and gives no exclusions or prerequisites.

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