bizhawk_step

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

No annotations are present, so the description carries the full burden of behavioral disclosure. The description does not state effects (advancing emulation state), whether this is a read-only or mutating operation, whether it requires an active emulator session, or what happens if frames is unreasonable. Calling it a 'wrapper' hints at delegation but reveals nothing about side effects.

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 short sentence with zero wasted words. Extremely efficient, though it is arguably under-specified rather than tautologically concise.

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 one parameter, no output schema, no annotations, and a parameter of unclear semantics (0% coverage), the description is too thin to fully enable correct invocation. The 'GB-compatible wrapper' framing is useful but doesn't compensate for the missing behavioral and parameter details. Sibling tool overload (bizhawk_step among many bizhawk_* variants) further raises the bar for differentiation, which this description does not meet.

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 single parameter 'frames' has 0% schema description coverage, and the description provides no semantics for it beyond the name itself. An agent reading 'frames' can infer it's a count, but nothing states whether it means output frames, input frames, or emulated frames per step; the description offers no added meaning over 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?

The description 'GB-compatible wrapper for emulator_step' identifies the verb (step) and the resource (emulator_step), but it's vague about what 'step' actually does. The term 'GB-compatible' suggests Game Boy compatibility, but the description never states that this advances the emulator by a given number of frames. It relies on the sibling tool emulator_step to convey meaning implicitly rather than stating its own purpose.

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?

No guidance is given on when to use this wrapper vs the generic emulator_step, or vs bizhawk_tap/hold/release alternatives. The 'GB-compatible' prefix hints at some specialization but doesn't explain the distinction, such as whether the underlying emulator is fixed to GB or how frames map to real time.

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