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

Beyond the destructiveHint/idempotentHint annotations, the description discloses the preview-then-commit gate, the prohibition on fabricating approval, idempotency retry semantics, and a fallback when cruise tools are unavailable. The generic patch sentence ("Omitting a field preserves it; null clears nullable fields") is partly boilerplate since the request schema sets additionalProperties=false and only exposes a ReorderDays operation, so it adds less than it appears to.

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 preview/commit workflow is front-loaded and the ordering of information follows the actual call sequence. The closing segment-type and unavailability guidance is relevant but reads as appended policy rather than core to reordering, slightly diluting focus.

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 destructive, versioned mutation with an output schema present, the description covers the safety workflow, retry behavior, and scope boundaries well. It doesn't explain what the preview payload contains, though the output schema is expected to carry return values.

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?

With only 50% schema description coverage, the description usefully discloses where expectedVersion comes from (cruise_get) and how idempotencyKey should be reused on retries, which the schema does not say. It still leaves tripId and the nullable cruiseId unexplained, and the patch/null note does not map cleanly onto the actual nullable field.

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 reorder operations atomically" states a specific verb (reorder), resource (cruise days), and the two-phase execution model in one sentence. It clearly separates this tool from siblings like checklist_items_reorder or library_list_items_reorder and from cruise_day_update.

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 prescribes the exact workflow: call cruise_get for expectedVersion, omit confirmationToken to preview, show the user, then repeat the unchanged request with the token only after approval. It also states the retry rule (reuse idempotencyKey), the domain boundary (commercial cruise reservations and sea/port days use cruise_* tools), and the explicit exclusion that Activity/CruiseActivity must never substitute for a cruise day while shore excursions remain valid.

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