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

The annotations already establish readOnly=false, destructive=false, and idempotent=true, so the safety profile is known. The description adds patch-like partial-update semantics ('only the fields that change') and ID provenance from get_trip, which are behavioral details beyond the annotations. It does not mention side effects like hotel_name triggering a re-lookup, but that is disclosed in the schema.

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?

Two sentences with no filler. The core verb comes first, the required identifiers and partial-update rule follow, and the flight-specific segment rule is folded into the second sentence. Every clause adds operational value.

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 large nested schema with no output schema, the description covers the selection and primary invocation pattern: IDs, partial update, per-type keys, and flight segments. The schema's rich property descriptions fill in field-level requirements such as hotel_name lookup behavior and cancellation rules. A small gap is that the description doesn't state what the call returns, but that is not essential for mutation.

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 29%, so the description carries real weight here. It correctly identifies the two required identifiers and their source, and encodes the central rule: put changed fields under the key for the booking type, and for flights only changed segments with segment_id. It doesn't enumerate every type key or field-level nuance, but the schema's own descriptions cover those details.

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 'Change a booking' — a specific verb and resource — and the title reinforces it. It is clearly distinct from add_booking and delete_booking, and the phrase 'under the key for its type' signals the per-type update model without requiring the agent to open the schema.

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 concrete invocation guidance: pass trip_id and booking_id from get_trip, include only changed fields under the appropriate type key, and for flights send changed segments with their segment_id. It does not explicitly contrast with add_booking or delete_booking, but the update-scope instruction is enough context to select this tool.

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