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

Beyond the annotations (readOnly/openWorld/non-destructive), it discloses substantial behavior: role-based visibility (customers/agents get availability-only, staff get full detail), the exact fields suppressed (driver name, vehicle, plate, position, distance, fleet size), an ETA rounded to 5 minutes, a 5-car cap, and the rule that driver details are released only after a booking is confirmed. This is exactly the kind of context structured fields 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 the core action and target formats, then the return/visibility rules; it is a dense paragraph rather than a bloated one, and each clause carries information. It runs slightly long, but no sentence is pure padding.

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 carries the return-value burden and does so fully: what the response contains (car type, seats, rounded ETA, per-car-type summary), what it omits, and how it differs by caller role. An agent has enough to call and interpret the tool 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 real meaning the schema lacks: the enumerable set of airport codes, that min_pax enforces a vehicle size tier, that include_on_job is for staff seeking busy drivers, and a customer-facing result cap of 5 cars even though the schema's limit allows 25. That role/limit interaction is important context above the schema.

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 opens with a precise verb+resource ('Find the closest available drivers to a location using live fleet GPS') and scopes it to availability, which implicitly separates it from route/tracking siblings like track_driver and get_driver_route. It never names a sibling explicitly, so an agent gets clarity but not direct routing guidance.

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 lists the accepted target formats (airport code, postcode, lat+lng) and role-dependent behavior, which implies usage, but gives no explicit when-to-use/when-not or alternatives ('use this instead of X when...'). The agent must infer that this is the pre-booking availability lookup.

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