Finish and deliver evidence

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

Annotations declare destructive=true, but the description adds substantial context beyond them: the VM is destroyed and unregistered, delivery/snapshot/outcome/review are reported as separate facts, a verified package is not a passing test, and failure semantics (missing declared outputs go to incompleteExtractions and do not block delivery; other failures retain the VM for a corrected attempt). This is exactly the extra behavioral disclosure the lower bar with annotations calls for.

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 action sequence is front-loaded, and each following sentence carries a distinct caution (separate facts, call-before-return, failure handling). It is dense and slightly long, but no sentence is 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 no output schema, the description carries the return-value burden and does so: it enumerates the reported facts (delivery, snapshot completeness, execution outcome, human review) and the incompleteExtractions field. Combined with the destructive/failure semantics, an agent has what it needs to call and interpret this tool.

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, so per the baseline rule a 4 applies. The description references `incompleteExtractions`, but that is an output field rather than an input, so there is no additional parameter meaning to add.

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 multi-step verb chain (extract outputs, deliver/verify package, destroy VM, unregister) with a clear resource, and names the sibling alternative relay_release. An agent can distinguish it from relay_search/relay_extract/relay_stage without opening schemas.

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 explicit timing ('Call this, or relay_release, explicitly before you return, since ending the session does not do it for you'), which is strong when-to-use guidance. It names the alternative but does not state the condition that selects relay_finish over relay_release, so the choice between the two is left partly to inference.

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