comfy_restart

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

Adds value beyond the annotations by disclosing the validation timing ('selector is checked immediately before the mutation') and the behavioral guarantee about not falling back to port 8188. These details enrich the destructiveHint/idempotentHint annotations without being redundant. Slightly short of 5 because 'safely' is never explicitly defined (e.g., graceful shutdown behavior).

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 crisp sentences with key information front-loaded. The critical first sentence states the purpose clearly. The only minor inefficiency is the slightly awkward 'First call...' mid-paragraph construction, but overall there is minimal waste and strong scannability.

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 destructive, non-idempotent-free operation with 5 params, the description covers the safety selector flow (doctor → pass back ID) and port behavior. However, it omits what triggers the timeout, what wait_for_health verifies, and the state of running jobs on restart. Given the output schema exists, return values need no explanation, but the operational semantics could be richer for a destructive 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?

With 0% schema coverage, the description bears the full burden of parameter explanation. It meaningfully addresses 2 of 5 parameters: expected_instance_id and expected_pid map to 'pass back either its instance_id or listener PID.' However, confirm, timeout_seconds, and wait_for_health are entirely unexplained, leaving the agent to guess their purpose.

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?

Description clearly states 'Safely restart the selected local instance through Manager V2.' — specific verb (restart) + resource (selected local instance) + mechanism (Manager V2). The additional detail that 'ComfyPilot never falls back to launching a competing server' clarifies the tool's scope and differentiates it from sibling lifecycle tools like comfy_launch_server, comfy_stop_server, and comfy_interrupt.

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?

Provides an explicit prerequisite workflow: 'First call comfy_instance_doctor and pass back either its instance_id or listener PID.' This names a specific sibling tool as a precondition. However, it doesn't fully cover when to use this over alternatives like comfy_emergency_stop or comfy_launch_server, leaving some exclusion logic implied.

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