Disconnect

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description contributes the fact that what gets destroyed is a cable connection into a specific input port, but it omits error behavior when no cable is present and whether the operation is idempotent or reversible.

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?

One sentence, no filler, with the action and the addressing format both front-loaded. Nothing is wasted or buried.

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 one-parameter tool with no output schema, the description supplies what the schema does not: the meaning and format of the address. It stops short of describing post-conditions (what the patch looks like after, whether a dangling module remains), which keeps it from a 5.

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% – the only structured constraint is a regex pattern – so the description carries the burden and delivers: it explains that `to` is an input address in "moduleId:port" form. It could still state whether the port half must exist or be free.

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?

"Unplug the cable going into an input" is a specific verb plus resource, and it names the target as an input rather than an output port. An agent can distinguish it from `connect` and `remove_module` on the sibling list, though the description never explicitly frames it as the inverse of `connect`.

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 is only implied by "unplug the cable going into an input" – the agent must infer that this is the undo/removal counterpart of `connect`. There is no statement of prerequisites (must a cable exist first?), no when-not guidance, and no mention of `undo` as an alternative path.

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