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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the risk profile is known. The description's "cannot be undone" largely restates destructiveHint, and it never says whether dependent data (bookings, links, places) is cascade-removed or whether confirmation/permissions are required. The cruise-routing caveats are genuinely useful context that annotations cannot carry, which keeps this above a 2.

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 irreversibility warning are correctly front-loaded, but the text then spends four sentences on cruise routing and repeats the same rule twice ("use cruise_* tools" / "require the dedicated cruise tools"). A single consolidated sentence about cruise types would have earned the same guidance in half the space.

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 one-parameter destructive delete with annotations covering the safety profile and no output schema, the description supplies the essential action plus the important domain caveat about cruise segment types. The remaining gap is scope of deletion — what else disappears when a segment is removed — which matters for a destructive operation but is partially mitigated by the explicit irreversible warning.

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?

There is a single required parameter with 100% schema description coverage, so the schema fully documents segment_id. The description adds no format hints, no indication of whether a segment ID differs from a cruise day ID, and no guidance on what a valid ID looks like. Baseline 3 applies when the schema does the work.

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 gives a specific verb and resource ("Delete a segment from a trip"), which is immediately actionable and distinct from sibling mutators like library_list_item_delete or trip_delete. The remainder of the description is devoted to cruise-type routing rather than further clarifying this tool's own scope, so differentiation is strong against cruise siblings but absent against non-cruise ones.

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 explicitly states a when-not case: commercial cruise reservations and sea/port days must go to cruise_* tools, never substitute Activity/CruiseActivity, and shore excursions are still valid Activity/CruiseActivity. It also gives a fallback behavior (explain the limitation and ask for clarification) when cruise tools are unavailable. It does not address when to use delete versus segment_update or trip_delete, and the cruise rules are restated twice rather than stated once.

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