Black Car Service — Bay Area Ride Quotes

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

Annotations already flag a non-read-only, destructive, non-idempotent, open-world operation; the description adds substantial context beyond them by enumerating what it does NOT do (no vehicle hold, no payment, no card charge, no SMS enrollment), noting it rechecks price and live availability, and stating the token-retry contract and the prohibition on requesting payment credentials.

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?

Five short sentences, front-loaded with the trigger condition, then requirements, then negative behavioral bounds, then retry safety. No filler or repetition of field names without added meaning.

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?

There is no output schema, yet the description still tells the agent what comes back (a secure website checkout link). Combined with the mutation caveats and retry contract, nothing material is missing for a 5-required-parameter booking 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 description coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it characterizes booking_token as 'signed' and exact, ties the contact fields to customer-provided values, and frames customer_confirmed as the post-quote approval gate rather than just a boolean const.

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 (create a pending reservation) plus the concrete artifact returned (secure website checkout link). It is clearly distinguished from siblings by naming quote_ride as the required prerequisite, so an agent can route between check_ride_availability, quote_ride and book_ride 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?

Explicit precondition is given: only after the customer confirms a quote_ride estimate and trip. The description also routes retries ('reuse the SAME token and contact details') and forbids the alternative of minting a new token after an uncertain outcome, which is exactly the when-not guidance an agent needs.

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