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

Goes well past annotations: payment is always on Stripe, the agent never charges, the 30-minute hold auto-releases the unit, price is the public rate with no coupons, and idempotency keys on category+dates+pax+email. These add real behavioral context even though idempotentHint/destructiveHint already flag the safety profile.

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 WHEN, then returns, payment, idempotency, and a worked example — a well-ordered structure. Minor waste: the 30-minute hold is stated twice ('~30 min' and 'hold_minutes: 30'), and the return-field list partly duplicates the existing output schema.

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?

For a 10-parameter mutation with real consent and payment consequences, nothing an agent needs is missing: preconditions, consent rule, hold expiry behavior, pricing rules, idempotency, and a concrete example are all present. The output schema covers return shape, so the description's field enumeration is surplus rather than a 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 coverage is 100%, so the baseline is 3; the description earns above that by defining the idempotency tuple that actually determines replay behavior and by making the accepted_terms semantics a consent rule rather than a plain boolean. It stops short of 5 because per-parameter formats remain the schema's job.

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?

A specific verb+resource ('create booking request') whose WHEN clause makes the position in the booking flow unambiguous relative to search_availability and get_quote. An agent knows exactly what is being produced (a booking_id plus a hosted checkout_url).

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 WHEN block lays out three hard preconditions (category+dates chosen, contact details gathered, explicit policy acceptance) and an explicit prohibition ('never set accepted_terms: true on your own'). This is a genuine when/when-not rule rather than an implied flow.

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