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

Annotations cover safety (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds genuinely new behavior beyond them: the booking does not exist until SMS phone confirmation and payment (or on-site payment), the slot and basket are re-validated against live capacity, and bookingUrl is fragile — any alteration breaks the pre-fill. That is the kind of operational detail annotations cannot carry.

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-loaded with purpose and kept to a handful of dense sentences, each carrying real information. Minor slack in the parenthetical enumeration of pre-filled fields and the arrival/totals clause, but nothing wasted at the sentence level.

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 describes the return payload (bookingUrl, arrival times, online vs on-site totals) and the lifecycle of the booking. The one gap is failure behavior: it says the slot is re-checked against live capacity but never says what the agent gets if the slot or basket no longer holds.

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 80%, so the schema already documents date, centerSlug, serviceIds and vehicleType, including the enum. The description only loosely maps its five inputs onto the pre-filled form fields ('centre, day, slot, vehicle and services') and adds no format, ordering or validation detail beyond the schema, so the 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?

The description gives a specific verb and resource ('prepares a booking without creating it') and immediately scopes what it returns (bookingUrl plus arrival times and totals). It is clearly distinguishable from quote_booking (pricing) and find_centers/search_available_slots (discovery) without opening any 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?

Usage context is clear: it belongs at the end of the funnel, consuming the basket that 'quote_booking priced' and re-checking a slot from 'search_available_slots', and it explicitly is not the creation step. However, it never states the ordering as an instruction or names an alternative for when the pre-check fails, so it stops short of explicit when/when-not guidance.

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