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

Annotations already declare destructive/openWorld/idempotent, so the bar is lower, yet the description still adds real value: no restart required (no downtime), an explicit refusal condition, and the required scope network.write. It does not state whether the removed card is recoverable or what the response confirms, but the pre-call behavioral picture is strong.

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?

Three short sentences, each carrying a distinct fact (effect, no-restart, refusal, scope) with the primary effect front-loaded. No filler or repetition of the 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 destructive two-parameter mutation with no output schema, the description covers effect, downtime, failure mode, and permission scope. Missing only the return value and whether a partially configured machine (no VPC attached) errors out.

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% and both parameters (`vm`, `vpc`) are documented with cross-references to list_vms/create_vm and list_vpcs/create_vpc. The description adds nothing about them, so the baseline 3 applies.

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?

"Removes the machine's private address and card, without a restart" names the specific mutation and its two effects, which is well beyond restating the name. It is clearly the inverse of connect_vpc in the sibling list, though the description never names that counterpart explicitly.

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?

"Refused for the only network of a machine with no public address" gives a concrete precondition that determines whether the call will succeed, which is exactly the kind of guidance an agent needs before invoking it. It stops short of naming a fallback (e.g., attach a public address first, or use connect_vpc to reverse).

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