Set DNS preferences

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

Discloses a non-obvious failure mode and ordering dependency (enabling MagicDNS fails without nameservers) that annotations do not convey. Annotations already cover readOnly=false, idempotent=true, and destructive=false, so the description adds meaningful behavioral context beyond those structured hints.

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 sentences with no filler: the first defines the operation, the second provides a targeted fallback instruction. The important operation is front-loaded, and the caveat is placed where it is most useful.

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 tool with idempotent and non-destructive annotationsasi, the description covers the operation, the parameter meaning, and a real-world failure scenario with remediation. It does not describe return values, but no output schema is present and the operation itself is simple enough that this is a minor gap.

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 the schema already documents magicDNS as a boolean. The description reinforces that the boolean enables or disables MagicDNS and hints at the enabling side effect, but it does not substantially go beyond the schema for the single parameter.

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 ('Set DNS preferences for your tailnet') and gives a concrete example (enabling/disabling MagicDNS). It is clearly distinct from get_dns_preferences by the set/get contrast, though it does not explicitly disambiguate from set_dns_configuration or set_nameservers.

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?

Provides a concrete usage caveat: enabling can fail when no nameservers exist, and directs the agent to call tailscale_set_nameservers first in that case. This is an explicit conditional alternative, though it does not broadly discuss when to prefer this over set_dns_configuration or when to check get_dns_preferences.

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