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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description goes beyond them by explaining the two-phase approval gate, atomicity, and idempotency-key reuse for retries — real added context for a destructive mutation. However, the line 'omitting a field preserves it; null clears nullable fields' is generic boilerplate that does not match this schema, where every request field is required and the only operation is RestoreDay with a fixed dayId.

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 core action and the preview/commit protocol are front-loaded in the first two sentences, and the segment-type warnings are placed after the operational instructions. It is a long paragraph with some padding — the field-preservation sentence and the 'if cruise tools are unavailable' clause could be trimmed — but nothing is buried ahead of the essentials.

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, nested-schema mutation with an output schema supplied, the description covers the workflow, approval gate, version requirement, and retry semantics that an agent actually needs. The main residual gap is that it never states plainly what a 'restore' recovers (a previously deleted cruise day), which is implied by the name rather than said outright.

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 only 50%, but the description compensates by explaining the three semantically tricky inputs: expectedVersion (the exact value from cruise_get, including the trip-only read), confirmationToken (omit to preview, repeat to commit), and idempotencyKey (reuse on retries). The nested operations array and cruiseId are left to the schema, keeping it short of a 5.

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 first sentence names a specific verb (restore), the exact resource (cruise day), and the defining behavioral trait (atomic preview-then-commit). It also fences off the wrong resource type by warning against substituting Activity/CruiseActivity segments for a cruise day, so an agent can separate this from segment-level tools without opening a 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?

The description prescribes an explicit sequence: call cruise_get first for expectedVersion, omit confirmationToken to preview, show changes to the user, then repeat the unchanged request with the token only after approval. It adds a retry rule (reuse idempotencyKey) and a fallback behavior when cruise tools are unavailable, leaving little to inference.

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