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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, and the description adds substantial context beyond them: the atomic multi-operation commit, the mandatory human-approval gate before the token is supplied ('Never manufacture approval'), retry safety via idempotencyKey, and the omit-preserves vs null-clears field semantics. That is exactly the operational context an agent needs for a destructive mutation.

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?

Front-loaded with the core preview/commit flow, then the version, idempotency, and null-semantics rules, then routing guardrails. It is dense but nearly every sentence carries a constraint. The closing sentence about cruise tools being unavailable is a slight tangent but still actionable.

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, atomically-batched nested mutation with an output schema present, the description covers the approval workflow, version concurrency, idempotency, field-null semantics, and cross-tool routing. Nothing an agent needs in order to call this safely is missing.

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 50% and the nested operations payload carries most of its own field-level descriptions, so the schema does much of the work. The description still adds real meaning for the top-level parameters: expectedVersion must come from cruise_get (including a trip-only read before cruise creation), confirmationToken is the preview/commit switch, and idempotencyKey governs retries. It does not explain the operations array structure, but the schema covers it.

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?

States a specific verb pair and resource: 'Preview and commit cruise day update operations atomically.' The two-phase nature and the resource (cruise day) are unambiguous, and the name-plus-description combination clearly separates it from cruise_day_create, cruise_day_delete, and cruise_day_restore.

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?

Explicitly prescribes the sequence (call cruise_get for expectedVersion), the preview vs commit condition (omit confirmationToken to preview, then repeat with the token after approval), retry behavior (reuse idempotencyKey), and routing rules ('For commercial cruise reservations and sea/port days use cruise_* tools', 'Never substitute Activity, CruiseActivity'). It even covers the fallback when cruise tools are unavailable, which is unusually complete.

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