comfy_stop_server

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

Beyond annotations (destructive, idempotent), the description discloses that it invokes comfy-cli, requires explicit confirmation or MCP elicitation, only targets explicitly selected non-Desktop servers, and details three distinct return shapes including the failure case when comfy-cli is not on PATH. The idempotent behavior is consistent with the 'failed' status when no server is running.

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 front-loaded with a precise one-sentence purpose, then a focused paragraph on exclusions/alternatives, followed by clearly labeled Args and Returns sections. Every sentence adds value, with no redundant fluff.

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, optional-parameter tool, the description covers prerequisites (comfy-cli on PATH), selection logic, confirmation flow, return shapes, and common failure modes. The output schema exists, but the description still succinctly explains the three JSON shapes, making the tool fully understandable without external docs.

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 has 0% description coverage, but the description compensates fully by explaining each parameter's purpose: workspace selects the install path, expected_instance_id comes from comfy_instance_doctor, expected_pid is a listener PID selector, and confirm gates the destructive action. This adds real meaning beyond raw schema names and types.

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 specific verb+resource: 'Stop an explicitly selected non-Desktop ComfyUI server via comfy-cli.' It clearly distinguishes this tool from sibling tools like comfy_restart and comfy_launch_server, and clarifies it does not handle Desktop-supervised instances.

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: 'Desktop-supervised instances are never handed to comfy stop' and gives alternatives: 'Use Comfy Desktop itself for a full stop, or comfy_restart for Manager V2 restart.' This is strong 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.