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

With readOnly/idempotent/destructive/openWorld annotations already covering the safety profile, the description still adds real value: the no-side-effect guarantee against basket/hold/order, and the pricing rule that a 7th passenger requires a second vehicle. It stops short of describing how the cheapest option is chosen or what happens when no list price exists.

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?

Three dense sentences, front-loaded with the core action and output contents, then constraints, then inputs. The parenthetical about the 7th passenger is slightly clunky but carries real business logic, so nothing is wasted; it is just packed tightly rather than elegantly.

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?

An output schema exists, so return values need no prose, and annotations cover safety. The description still supplies the two things structured data cannot: the read-only/no-side-effect scope and the conditional district requirement. An agent has everything needed to invoke this correctly.

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 3 is the baseline, but the description adds genuinely new information by stating which inputs are needed and, crucially, the conditional 'Istanbul also needs district' — a requirement the schema presents only as an optional string. That conditional dependency is not derivable from the structured fields alone.

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 ('prices one transfer for a party from the stored list price') and even enumerates what the quote contains: vehicles needed, price per vehicle, total, cheapest option. The phrase 'Reads only: no basket, hold or order' separates it from booking/basket-oriented siblings, and the name parallels quote_hotel_stay without ambiguity.

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?

It gives an explicit exclusion — 'Reads only: no basket, hold or order' — which tells the agent this is a pricing check, not a purchase step, and it lists the minimum inputs needed to run it. It does not, however, name a sibling alternative (e.g. search_transfers) for the case where the agent only has a destination rather than a slug.

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