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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description still adds real value: atomic execution, preview-versus-commit semantics with an explicit "never manufacture approval" guard, and the crucial partial-update rule that omitted fields are preserved while null clears nullable fields. It does not disclose that the operations array includes DeleteDay/RestoreDay/ReorderDays or what a failed atomic batch leaves behind, which matters for a destructive multi-op tool.

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 workflow is front-loaded in the first three sentences, which is the right ordering for a destructive tool. It drifts slightly at the end into segment-type policy and a contingency about unavailable cruise tools, which are relevant but dilate the core message.

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 tool whose schema nests six operation kinds across an array of up to 250 items, the description says nothing about which operations exist or how they compose atomically, leaving the agent to discover AddDay/DeleteDay/RestoreDay/ReorderDays purely from the schema. The workflow and versioning story are complete, and an output schema exists, but the operation surface is under-explained for this complexity.

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 50% and the description compensates meaningfully: expectedVersion is tied to cruise_get with the note about a trip-only read before creating a cruise, idempotencyKey is tied to retry reuse, and confirmationToken's presence-or-absence is defined as preview versus commit. The individual operation kinds and their field semantics are left entirely to 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?

"Preview and commit cruise update operations atomically" gives a specific verb pair and resource, and it names cruise_get as the prerequisite source of expectedVersion. It does not distinguish this batched tool from the day-level siblings (cruise_day_update, cruise_day_create, cruise_day_delete, cruise_reorder), even though its operations array overlaps with them, so an agent still has to guess which entry point to use.

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 preview/commit sequence is spelled out explicitly: call cruise_get first, omit confirmationToken to preview, show changes, then repeat the unchanged request with the token after approval. Retry behavior via idempotencyKey is also stated. What is missing is any when-to-use guidance relative to the cruise_day_* siblings that perform similar per-day mutations.

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