restart_service

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds behavior the annotations cannot convey: a required two-step confirmation flow, the brief loss of this connection, and the fact that a klipper or moonraker restart terminates an active print. That is exactly the kind of consequence disclosure a caller needs before invoking a destructive 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?

Three short sentences, each doing distinct work: scope and examples first, the confirmation protocol second, the destructive consequences last. Themost severe consequence is saved for the end where it lands, and there is no filler or repetition.

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?

An output schema exists and the annotations cover the safety profile, so the description need not explain return values. However, for a destructive four-parameter tool with zero schema description coverage, the omission of any explanation of the confirm/confirm_token handshake leaves a real gap an agent must guess at.

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 percent across four parameters, so the description carries the full burden and only partially meets it. The verbs 'restart, stop, or start' hint at the values of the action parameter, and 'two-step confirmation' gestures at confirm and confirm_token, but neither the parameter names, the allowed action values, nor how the confirm token is obtained and supplied are explained.

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 gives a specific verb set (restart, stop, start) on a specific resource (systemd service on the printer) and lists concrete examples like klipper, moonraker and crowsnest. It falls short of 5 because it does not distinguish itself from close siblings such as restart_klipper_host or restart_firmware, which an agent could easily confuse with this tool.

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?

Usage context is implied rather than stated: the agent learns the tool acts on systemd services and that restarting klipper or moonraker drops the connection and ends a print, which is a caution about when it is dangerous. There is no explicit when-to-use or when-not-to-use guidance relative to restart_klipper_host or restart_firmware, so the choice among these overlapping siblings is left to inference.

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