Sb3 Vm Run

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses key hidden behaviors: budgets of 0 are omitted because the sidecar's zod schema rejects explicit 0, None values are not forwarded, and paced=False disables per-frame sleep. This adds genuine context beyond the schema, though 'proxied' remains unexplained and side effects are only implicit.

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 compact and front-loaded with the core action and return value. The technical quirks are placed in parentheticals and short clarifying sentences, and every sentence earns its place. It could be slightly more structured, but it is appropriately sized for the tool's complexity.

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 four parameters, no annotations, and an output schema, the description covers the important edge cases: default forwarding, zero-budget omission, and the deterministic pacing behavior. It omits preconditions like needing a loaded VM, and it doesn't explicitly route the agent to related tools, but it is otherwise sufficient for correct invocation.

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?

The schema provides no parameter descriptions, so the description must compensate. It does explain that seconds/frames are budgets, that 0 causes omission, that untilIdle/paced are only forwarded when set, and that paced=False disables per-frame sleep. It stops short of defining what untilIdle actually means, but the added semantic value is strong.

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 and resource: 'Advance the headless VM; returns state + event timeline.' This clearly conveys what the tool does, but it does not explicitly differentiate itself from sibling tools like sb3_vm_step_frame or sb3_vm_run_until, which could imply similar behavior.

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?

There is useful usage guidance, such as 'paced=False runs the budget back-to-back with no per-frame sleep, which is what deterministic step-debug wants,' and the explanation of when sidecar defaults apply. However, it never states when to choose this tool over sb3_vm_run_until or sb3_vm_step_frame, nor gives explicit when-not conditions.

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