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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally; the description adds real value on top by specifying what is destroyed (the disk), that billing stops, and that workspace storage remains billed per GB-month. It does not state permission or ownership prerequisites, which keeps it short of a 5.

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?

Two dense sentences, front-loaded with the primary effect, followed by the destruction warning and the mitigation. No filler and no repetition of the tool title.

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 two-parameter destructive lifecycle tool with no output schema, everything an agent needs is present: what stops, what is irreversibly lost, how to mitigate it, and the cost consequence of mitigating. Missing auth details are minor against an otherwise complete picture.

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 coverage is only 50%, with only save_workspace documented, so the description must compensate. It does: it explains exactly what save_workspace preserves (/workspace), that the data returns on next launch, and that retained storage is billed per GB-month, adding meaning beyond the schema's one-line default explanation.

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 verb and resource ('Stops a server') and immediately scopes the effect ('and its billing'), then adds the critical side effect that the disk is wiped. This is unmistakably distinct from get_server, launch_server, and list_servers without needing to name them.

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 implies the when (you want to stop paying for a server) but never states when to use it versus alternatives, and never explicitly warns that this is the wrong tool if the workspace must be preserved without setting the flag. The save_workspace clause is the only conditional guidance offered.

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