Configure a service

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

Annotations flag destructiveness/open-world, and the description adds real behavioral context beyond them: funnel publishes to the entire public internet and requires user confirmation, omitting 'allow' leaves the service readable by every tailnet member, the daemon installs itself unless no_daemon_install is set, announcements go to stderr, and setup returns URL/enrollment evidence immediately. These are exactly the consequences an agent needs to reason about before invoking.

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?

It is a dense paragraph rather than a bulleted list, but it is well front-loaded: the highest-risk behavior (public internet exposure) comes first, followed by default reachability, sibling routing, install behavior, and return behavior. Every sentence carries information, though the density makes it slightly harder to scan than it could be.

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 20-parameter mutation tool with nested objects, the description covers the critical decision points (public exposure, default access, install side effect, return timing) and an output schema exists so return values need no elaboration. It leaves the many secondary parameters entirely to the schema, which is acceptable at 90% coverage but not exhaustive.

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 description coverage is already 90%, so the baseline is 3; the description still adds meaning by explaining the default-open behavior of 'allow', the public-exposure semantics of 'funnel', and the install-suppression role of no_daemon_install. It does not, however, touch several other parameters (tags, health, request_limits, ephemeral), which the schema carries alone.

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?

Despite the generic name 'add', the description states a specific action and resource: it writes a registry entry for a proxy, file, or TCP service on the user's tailnet, or publishes it publicly via funnel. It explicitly separates itself from the sibling 'share' ('Use this instead of share...'), so an agent can route correctly without opening either 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?

It names the alternative tool and the condition that selects it ('use this instead of share when the user wants a named, configured service rather than a one-shot share') and points to 'url' for polling pending endpoints. It also gives a clear when-to-ask rule for the funnel case.

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