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

Annotations already cover read-only/idempotent safety, yet the description adds substantive behavior: the price is the public checkout rate for a non-member with no discount code, and on unavailability `available` is false with `booking_url` falling back to the search page plus a hint. That is exactly the kind of context 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 WHEN / WHAT IT RETURNS / EXAMPLE structure, every sentence bearing information an agent needs. No restatement of the tool title or filler.

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?

Covers trigger, return payload, unavailability path, pricing semantics and a concrete call example — the whole decision loop for invoking this tool. The optional `children`/`language` gap is the only soft spot.

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 50%, so the description must compensate — and it does for the four required fields via the worked example and the date-range framing. `children` and `language` remain unmentioned in both description and schema, which keeps it below a 5.

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+resource (get an exact quote/total price) with the precise scenario: one fixed category plus a date range and guest count. The example question "how much is G4 from 8 to 15 June for 6?" makes the purpose unmistakable and separates it from search_availability.

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 gives a clear trigger condition (traveller has fixed ONE category and wants the exact total), and the fallback hint routes the agent to search_availability when the result is unavailable. It stops short of an explicit 'do not use this for browsing multiple categories' exclusion, but the routing is effectively covered.

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