Release the VM

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

Annotations declare destructive=true and idempotent=false, and the description goes well beyond them: evidence is retained, a failed release keeps ownership until destruction is verified, retry after failure is safe, and the no-lease case returns an error rather than guessing a lease. These are exactly the operational details an agent needs for a destructive teardown.

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?

Four dense sentences, front-loaded with the primary action and its contrast to relay_finish, then escalating to retry and error semantics. Every sentence carries distinct information, though the phrasing is slightly packed.

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 no-parameter, no-output-schema, destructive teardown tool, the description covers purpose, alternative routing, retry/idempotency nuance, ownership semantics, and failure modes. Nothing an agent needs to call it correctly 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?

The tool takes zero parameters and additionalProperties is false, so there is nothing to document; the description correctly adds no parameter noise. The baseline for a parameter-less tool applies.

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 action ('destroy the owned VM and unregister it') plus the intent ('abandon the task... without claiming the task succeeded'). It explicitly names the sibling relay_finish as the opposite case, so an agent can distinguish the two without opening any 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?

Gives an explicit routing rule: 'Use this instead of relay_finish when the task is not being completed.' It also covers retry conditions and error conditions (no owned lease, lease under another session identity), 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.