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

With no annotations, the description carries the full burden. 'Preview' and 'pre-confirmation' strongly imply a non-mutating operationcher. However, it never explicitly states that no record is created or changed, nor does it describe response contents beyond 'show the breakdown.' Some behavioral ambiguity remains.

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?

Four short labeled sections plus an example. Information density is high; each line adds either a constraint, a usage direction, or a data-shape clarification. The all-caps labels are stylistically heavy but aid scanning.

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?

The description covers purpose, timing, prerequisite data, and the object example. Missing, given no annotations or output schema, are explicit non-mutation guarantees-checklist, pricing details, or what the function returns. It is adequate but not fully self-sufficient for an agent deciding whether this operation is safe to call mid-booking.

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 covers all parameter names/types, so baseline is 3. The description adds a concrete example for the charges array and a warning that quantity must be a number, which highlights a likely failure mode. The prerequisite ('gathered all end data') also gives context for finalHobbs/finalTacho without duplicating schema text.

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 uses a specific verb–object pair, 'Preview the costs,' and frames it as a 'PRE-CONFIRMATION STEP' that 'show[s] the pilot the breakdown before generating the invoice.' This makes the tool's role clear, though it doesn't distinguish it from the similarly named sibling settle_booking or estimate_flight_cost.

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 description provides concrete usage context: a mandatory prerequisite ('gathered all end data and manual charges ONE BY ONE') and the intended moment to call it ('before generating the invoice'). It lacks explicit 'use instead of X' routing, but the timing and preconditions are specific enough to guide selection.

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