checkpoint_delete

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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds genuine behavioral context beyond that: disks are merged as a side effect, child checkpoints are deliberately left behind, and exact confirmations are enforced — all of which matter for a destructive operation.

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?

Three short sentences, front-loaded with the action and its scope, then the non-recursion caveat, then the confirmation requirement. No filler.

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?

With annotations covering safety and an output schema covering returns, the description is nearly complete for a 4-required-param destructive tool. The remaining gap is how an agent obtains a valid snapshot_id and the precise confirmation-matching rule.

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 0% across 4 parameters, so the description must compensate. 'Requires exact confirmations' signals that confirm_vm and confirm_snapshot_id are echo-checks of the identity parameters, but it never states they must match vm_name/snapshot_id or what happens on mismatch, leaving the mechanism to inference.

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?

Specific verb + resource ('Delete one checkpoint') with a stated scope boundary ('one checkpoint', 'child checkpoints are not recursively included'). It effectively separates the tool from checkpoint_create/checkpoint_restore by implication, but never names an alternative explicitly, so it falls short of full sibling differentiation.

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 destructive-delete context is implied by 'Delete one checkpoint', and 'Requires exact confirmations' flags a prerequisite, but the description never states when an agent should choose this over checkpoint_restore or checkpoint_list, nor any when-not condition.

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