Set private network DNS

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

Far exceeds the annotations: it discloses disruption risk to attached guests, the exact scope required (networking:read vs networking:manage, and that full/read defaults do not grant networking), backend ownership/feature/2FA enforcement, the fact that an accepted operation is pending rather than proven connectivity, and a full polling protocol for reason_code/reason_kind, plus idempotency-recovery rules. This is unusually rich disclosure for a destructive mutation.

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?

Purpose and the interruption warning are correctly front-loaded, but the back half is a long generic operation-polling/idempotency protocol that reads as boilerplate shared across many mutating tools. Much of it is operational guidance rather than tool-specific semantics, inflating the size without proportional per-sentence value.

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?

With no output schema and only 50% schema description coverage, the description compensates well on auth, safety, pending-vs-success semantics, and recovery. The remaining gap is the dns_mode mode values and the shape of the returned operation/resource the agent is told to poll.

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 50%, so the description must carry part of the burden; it meaningfully constrains dns_servers to custom mode. However, the three dns_mode enum values (provider/custom/none) are never explained, and the description does not clarify what each mode does to DHCP behavior, leaving the highest-impact parameter under-defined.

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 opening clause gives a precise verb+resource+scope: 'Replace the network's DHCP DNS mode and resolver addresses,' which clearly separates it from guest- or domain-level DNS siblings. It stops short of naming a specific alternative tool, so the differentiation is implied rather than explicit.

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 a concrete parameter-usage rule ('Use dns_servers only for custom mode'), a prerequisite sequence ('Read current capabilities and owned resource state first; obtain approval'), and a risk warning that changing/disabling interrupts guest name resolution. It never names a competing sibling tool to route the agent elsewhere, so it lands at 4 rather than 5.

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