vm_set_ttl

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

Annotations already mark the tool as destructive and non-read-only, but the description adds important non-obvious behaviors: confirm=False only previews and schedules nothing, confirm=True applies the TTL, the daemon must be running or nothing is deleted, it powers a running VM off first, and it refuses when VM identity or disks cannot be read. It also discloses the return dict and the persistence path.

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 description is dense but every sentence earns its place: purpose, preview behavior, safety instruction, intended use case, sibling routing, daemon prerequisite, side effects, persistence, and return type. The critical safety caveats are front-loaded, and the write nature is marked with [WRITE].

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?

No output schema exists, so the description correctly explains the return value as a dict with action and blast_radius, and enumerates the blast_radius contents. It covers confirmation semantics, failure modes, prerequisites, persistence, and side effects, leaving no major information gap for an agent to invoke the tool correctly.

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 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema for the confirm parameter, explaining exactly what false versus true does and what the returned blast_radius contains. It also clarifies that only confirm=True has destructive side effects. Other parameters like target and minutes are not elaborated, but the schema already documents them.

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 description opens with a specific verb and resource: 'Set a Time-To-Live (TTL) for a VM. The daemon auto-deletes it when expired.' It clearly distinguishes itself from the sibling tools vm_cancel_ttl and vm_list_ttl by describing the scheduling behavior and naming the cancellation/list alternatives.

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 says when to use the tool ('Use this for short-lived lab VMs so cleanup is not forgotten'), names the alternatives for cancellation and review, and provides a firm usage rule: do not set confirm=True on your own because the user has not seen the preview. It also warns about the required daemon, making the conditions of safe use clear.

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