restart_service

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

No annotations are provided, so the description carries the burden. It does disclose the medium-risk write nature, the undo implications, and the critical failure mode (killing its own connection). However, it does not describe what specific side effects a restart has on active connections/sessions, firewall state, or whether it takes the service down before bringing it up. Decent but not fully transparent for a mutation tool.

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?

The description is well-organized and front-loaded with the action and risk tag. The refusal note and dry_run note are valuable and concise. The Args block is somewhat redundant with the schema but serves as helpful inline documentation. Every sentence adds value, though it could be tightened slightly without losing information.

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 mutation tool with no annotations and no output schema, this provides good coverage: action, risk, examples, refusal cases, dry_run, and target semantics. The main gap is not documenting the return/confirmation behavior after a successful restart, but the description is notably complete for a tool of this complexity. The undo-related caveat shows deep contextual awareness.

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%, so the description must compensate for all 3 params. It explains service (name to restart, with examples), dry_run (preview), and target (firewall target, omit for default). All three are covered at a functional level. However, for service it doesn't enumerate valid values or where to find them, and 'target' semantics (what 'default' refers to) are vague. Adequate but could be richer.

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 opens with a clear [WRITE][risk=medium] tag and 'Restart a firewall service' with concrete examples (unbound, dhcpd, openvpn). This clearly distinguishes it from sibling read-only tools like interface_status or gateway_status, and from reboot/reconfigure. The verb+resource+examples are specific and unambiguous.

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 it (never on the management API service like nginx/configd because it kills the tool's own connection and undo cannot run), directs to console for those, and documents the dry_run preview option. Also notes 'target' is optional for default. This is exemplary when/when-not guidance.

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