safe_stop

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

Annotations provide destructiveHint=true, and the description goes beyond that by revealing specifics: the flush-required stop, the failure recovery (VM stays running on save failure), and the exclusion of unmanaged processes. It also discloses the refusal condition. This adds meaningful context without contradicting the annotation.

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 three sentences with no wasted words. The primary action and condition lead, followed by scope limitations and failure/refusal behavior. Each sentence earns its place, and the structure is clean and front-loaded.

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 destructive operation, the description covers all critical decision points: what it saves, when it stops, what it ignores, what happens on failure, and when it declines. No output schema exists, but the return value isn't essential for the agent's call decision. The description is complete for a zero-parameter tool with this complexity.

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 has zero parameters and the schema describes 100% of them (none). The description doesn't need to explain parameters. Baseline of 4 for zero-parameter tools is appropriate; there is no missing parameter information.

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 states a specific action — save all managed workspaces then stop the VM — and includes a necessary condition (Drive confirms flush). It explicitly distinguishes what it does not cover (unmanaged processes/files) and sets expectations about refusal. This clearly separates it from siblings like save_workspaces or runtime_status.

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 description conveys when it is appropriate to call (when you want to save and stop) and when it will refuse (if managed jobs are active). However, it does not explicitly name alternatives such as save_workspaces for saving without stopping or runtime_status to check job activity. It gives sufficient context for an agent to infer, but stops short of explicit routing guidance.

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