runtime_run

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

Goes well beyond the annotations: states headless default and that the window is placed off-screen and takes no focus, that script errors are reported but never stop the game, that the helper is loaded only for this run and writes nothing to the project, and that it returns session_id plus first-seconds output. These are exactly the operational traits a launching tool needs to disclose.

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?

Front-loaded with the core action and the isolation benefit, and every sentence carries information. The remaining text is dense with stacked clauses about headless mode, helper injection, and follow-up tools, which is close to the limit before it becomes a run-on.

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 7-parameter process launcher with no output schema, the description covers return values, defaults, windowed rationale, error behavior, and next steps. The one notable omission is how the run is terminated (runtime_stop) or what session_id is used for, which an agent must infer.

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 adds real meaning: helper is explained as enabling runtime_eval and runtime_input, and windowed is tied to the off-screen/no-focus behavior and the screenshot requirement. The collect/timeout/args nuances are left to the schema.

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?

Names a specific verb and resource ('Launch the game as its own process') and immediately differentiates it from the editor run-slot approach, noting that several agents can each run one at once. An agent can tell this apart from debug_run and runtime_status without opening a schema.

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?

Gives conditional guidance: headless is the default, use windowed=true only when runtime_screenshot is needed, and follow up with runtime_tree/runtime_inspect/runtime_output. It implies the contrast with an editor-run alternative but never states explicitly when not to use this tool (e.g. for debugging with breakpoints, use debug_run instead).

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