start

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

With no annotations, the description carries full behavioral disclosure. It reveals that the tool launches asynchronously, returns output from the first `wait` seconds, and stops any currently running program first – a critical destructive side effect. It also implies the process continues running in the background. This is comprehensive for a process-launch tool and leaves no major surprises.

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?

Two sentences deliver all essential information with no filler. The purpose is front-loaded, and each clause adds value: async behavior, parameters, return value, follow-up tools, and the stop-current-program caveat. This is model of concise, information-dense writing.

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?

Given no output schema, the description explains the return value (output from first wait seconds) and the lifecycle (monitor, interrupt). It also notes the preemptive stop of the current program. Missing details like error handling or behavior when no program is running are minor for a tool of this complexity; the description gives an agent enough to call it correctly and manage the process.

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%, so the description must explain all parameters. It does: `code` and `path` are introduced as alternatives ('pass code, or path'), and `wait` is defined as the number of seconds for initial output capture with a default of 1.5. It doesn't specify edge cases like supplying both code and path, but the core semantics are clear. Slight deduction for not noting mutual exclusivity or validation behavior.

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 states a specific action (launch), a clear resource (a long-running program via code or path), and explicitly distinguishes its asynchronous nature ('WITHOUT waiting for it to end') from synchronous alternatives. It also names the follow-up tools (monitor, interrupt) and the precondition (stops currently running program), making its role unambiguous among siblings.

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?

The description clearly indicates when to use this tool (for long-running programs like robot main loops and sensor logging) and guides the agent to complementary tools (monitor for reading output, interrupt for stopping). It doesn't explicitly name alternatives like exec or run_file or state when NOT to use it, but the context is strong enough that a capable agent would infer the distinction. A small gap is the absence of an explicit exclusion for short-lived programs.

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