Refresh vpnhop

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

The annotations only declare idempotentHint=true and destructiveHint=false, so the description carries the real burden and does so well: it discloses that all tunnels are closed, that they reconnect automatically on the next call, and exactly which artifacts get removed. There is mild tension with destructiveHint=false since images and containers are being deleted, but the framing (orphaned, dangling, old, auto-reconnecting) makes the non-destructive classification defensible rather than contradictory.

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, no filler, with the most consequential effect ('closes every tunnel') front-loaded and the reconnection caveat immediately after. The first sentence is a dense comma-list of cleanup actions, which is efficient but slightly harder to scan than a short bulleted structure would 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?

With no parameters, no output schema, and only two annotations, the description supplies everything an agent needs: scope of the disruption, that it self-heals on the next call, and the two situations that call for it. The only omission is any note about duration or service interruption while servers restart, which matters for a global cleanup operation.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate beyond confirming it is argument-free. Baseline 4 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?

The description enumerates concrete actions: closing all tunnels, recycling running vpnhop servers, stopping outdated/orphaned servers, and removing dangling tunnel containers and old runtime images. That is far more specific than the vague name 'refresh' and lets an agent distinguish it from the point-to-point 'connect'/'disconnect' siblings. It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.

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 gives concrete triggering conditions: 'Use after a tunnel gets stuck or after updating vpnhop.' That is clear when-to-use context. It never states when NOT to use it (e.g. for routine teardown, where 'disconnect' would be cheaper), so there is no explicit exclusion or named alternative.

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