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

With destructiveHint already set, the description goes well beyond the annotation by disclosing exactly what is destroyed (the server's own disk), what persists (attached volume, still billed, daily snapshots, managed databases), and that billing stops. This is high-value consequence detail for a destructive call.

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?

Front-loaded with the destructive verb and its immediate effect, then the persistence caveats, then the confirmation requirement and a docs link. Every sentence earns its place, though the clause chain about volumes/snapshots/databases is somewhat dense.

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 single-parameter destructive tool with no output schema, the description covers the critical unknowns: permanence, what survives, billing impact, and a user-confirmation requirement. Nothing essential to safe invocation 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?

Schema coverage is 100%, so the schema already documents machineId. The description adds meaning beyond the schema by telling the agent where to obtain it (lavela.project_overview) and by tying it to the confirmation step.

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 ('Permanently remove a server') and immediately scopes it with the machineId source. An agent can distinguish this from siblings like resume_compute, redeploy, or delete_project 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 clear context: use it to stop a server from running and being charged, and confirm the exact server with the user first. It doesn't explicitly name alternatives for adjacent operations (deleting volumes, snapshots, or databases), so routing is implied rather than enumerated.

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