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

Annotations already declare destructiveHint and openWorldHint, so the bar is lower, yet the description still adds the key behavioral facts: existing Nymwell records stop applying, changes apply immediately for owners/admins unless the workspace routes them to approval, and workflow.state is the source of truth. It stops short of describing auth failure modes or return payload, keeping it at 4.

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, zero waste. The accepted-value constraint comes first, the side effect second, the execution/approval condition third — a sensible front-to-back ordering for an agent deciding whether to call.

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, no-output-schema mutation, the description covers the side effect, the value constraints, and the synchronous-vs-approval execution path with a pointer to workflow.state. The only gap is that it doesn't say what the immediate-apply response looks like, but the approval path is explained well enough to act on.

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 0% and the schema only encodes minItems 2 / maxItems 13 without prose, so the description must compensate — and it does, spelling out both the hostname-count range and the literal 'default' value. The 'domain' parameter is left unmentioned, assuming it's self-evident.

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 (change) and resource (nameservers) plus the accepted values ('2 to 13 hostnames, or "default"'). This clearly distinguishes it from siblings like apply_dns_preset and apply_dns_to_domains, which also touch DNS but not the registrar-level nameserver delegation.

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?

Explains the consequence of pointing elsewhere (Nymwell records stop applying) and routes the agent to list_approvals when the change is queued rather than applied. It doesn't explicitly name sibling alternatives such as apply_dns_preset, but the immediate-vs-approval condition is made concrete.

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