runtime_step

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

No annotations are provided, so the description carries the full burden. It discloses that the operation is deterministic and requires a paused state, but it does not state prerequisites (e.g., game must be running and paused), failure modes, or side effects (e.g., execution of scripts during the step). This leaves important behavioral ambiguity.

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 a single, well-structured sentence that front-loads the verb and target, and the parenthetical adds the helpful synonym 'frame stepping' without unnecessary detail.

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 simple single-parameter tool with no output schema, the description covers the core action and condition, but it omits critical context about when the game must be paused, what happens if it isn't, and any side effects. The lack of annotations and usage guidance leaves the description only minimally sufficient.

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 already provides a clear description for the 'frames' parameter, and the tool description only repeats 'N frames'. With 100% schema_description_coverage, the description adds no additional meaning beyond the schema, so the baseline of 3 applies.

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 clearly states the action ('Advance the running game by N frames'), the resource ('running game'), and the condition ('while paused'), with the parenthetical 'frame stepping' distinguishing it from runtime_resume and runtime_freeze.

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 phrase 'while paused' gives clear context for when this tool operates, but it does not explicitly state when to prefer it over alternatives like runtime_resume or runtime_freeze, nor does it mention any exclusions or prerequisites. Usage is implied rather than fully specified.

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