run

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds genuinely non-obvious behavior beyond that: go blocks until the target stops, including when it is already running, and "Reaching the deadline leaves the target running: nothing stops it for you." That last point is a real operational hazard disclosed in prose. It does not describe permission or error behavior, so not a 5.

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?

It is short and front-loaded, leading with the action vocabulary before the behavioral caveats, and nearly every sentence carries new information. A few clauses are tightly packed ("go waits until the target stops, also when it is already running") and read slightly clipped, but nothing is redundant.

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?

With no output schema, the description must carry return-value burden; it partially does by noting the reply says whether go reached the `until` address, and it explains the deadline-left-running outcome. It does not describe what a normal reply looks like after step/step_over/break, leaving a gap for a four-parameter control tool.

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 100%, so the baseline is 3, but the description still adds meaning: it ties `until` to the go action specifically and says the reply reports whether that address was reached, which the schema does not state. It also reframes deadline behavior in terms of the target being left running rather than just a numeric limit.

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-plus-resource framing ("Control the target") and enumerates the exact action vocabulary (go, step, step_over, go_up, go_return, break), so the tool's scope is unambiguous. It stops short of naming sibling tools (session_status, command, evaluate) to distinguish itself, which keeps it below a 5.

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?

It gives explicit when-not guidance: "break stops the target now... so to wait for a breakpoint use go, not break," which directly prevents a common misuse. It also explains the until condition on go. It does not contrast this tool with siblings like `command` or `evaluate`, so routing among tools remains implicit.

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