restart_service

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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes well beyond them: it explains the concrete consequence of restarting the management service (connection killed, restart unobservable, undo cannot run) and declares a refuse-list. That is the kind of behavioral context annotations cannot carry.

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?

Front-loads the [WRITE][risk=medium] tag then the purpose and the refusal rule, then the preview hint, then a compact args list. No wasted sentences, though the prose is slightly dense and could be trimmed marginally.

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 three-param destructive tool with no output schema, the definition covers safety, alternatives, and each parameter. It could say more about expected output or what 'reconfigure' family of siblings does vs. this, but the essential call information is present.

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 0%, so the description must carry parameter meaning. It does document all three params briefly (service, dry_run, target) and clarifies that target comes from config and can be omitted. However it adds no format details (e.g., accepted service-name spellings, target naming) and the service param lacks ambiguity resolution, leaving more to be desired given the coverage gap.

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 write operation on a specific resource (restart a firewall service), and even names concrete service examples (unbound, dhcpd, openvpn). The scope is unambiguous and distinct from siblings like apply_changes or reboot.

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?

Explicitly states when not to use the tool (the management-API services) and gives the alternative (console). Also points to dry_run=True as the preview path. This is exactly the when/when-not/alternative guidance a strong definition provides.

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