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

The description reveals significant non-obvious behavior beyond the annotations: duplicate confirmation codes cause an update rather than a duplicate, the result reports matched_existing_booking, omitting trip_id lets Plot auto-assign or create a trip, times are local without timezone, and unconfirmed data should be omitted. These are exactly the side effects and conventions an agent needs to know.

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?

The description is dense and front-loaded, with the core action and category rule in the first sentence. Every sentence adds a distinct constraint. It is a single wall of text rather than scannable bullets, but for the complexity involved the length is justified and there is no 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?

For a complex nested-object write tool with no output schema, the description covers the most important operational behaviors: category exclusivity, trip assignment, dedup, timezone handling, and data fidelity. It is missing an explicit description of the full return shape (beyond the matched_existing_booking marker) and error cases, but the schema supplies required field details.

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 only 17%, so the description must add semantic value, and it does: exact-one-of-category constraint, flight-segment grouping, trip_id omission behavior, and confirmation-code dedup semantics. It does not enumerate every field, but the schema's own nested property descriptions carry that weight, and the top-level inter-parameter rules are the critical missing piece.

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 specific verb and resource: 'Save one booking to Plot', then enumerates exactly which record types are accepted (flight, hotel, car rental, transport, plan). It clearly distinguishes this tool from create/update/get/list trip siblings by focusing on booking creation and even clarifies the dedup-to-update nuance.

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 explicit usage rules: 'Fill in exactly one of flight, hotel, car_rental, transport or plan' and instructs to send all flight segments together. It also names get_trip as a check before resending a booking without a confirmation code. However, it does not explicitly contrast add_booking with update_booking or state when not to use this tool.

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