emulator_step

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

With no annotations at all, the description carries full burden. It discloses the max frames per call (600), which is useful, but doesn't say whether this is a blocking call, whether it affects emulator state deterministically, what happens on error, or whether frames advanced are actual CPU frames vs game frames. The 'neutral/released' qualifier hints at simulator behavior but is unspecified.

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?

Single efficient sentence that conveys core function and the key constraint (max 600). No wasted words. Could benefit from minimally more parameter detail but is appropriately terse.

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?

It's a state-mutation tool (advancing time) with no annotations, 0% param coverage, no output schema, and a 'target' param that's unexplained. Given the sibling presence of bizhawk_step and many emulator variants, the description doesn't clarify target semantics or how step results are observed (via emulator_status/screenshot presumably), leaving significant gaps for agent decision-making.

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 compensate. It explains 'frames' (the step count) and the max limit, but doesn't explain the 'target' parameter at all — whether it selects emulator instance (gb vs something else), and why it defaults to 'gb'. The 'target' parameter is entirely undocumented.

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?

Clear verb+action: 'Advance the emulator by N neutral/released frames.' This distinguishes from siblings like emulator_tap/hold/release which are input actions, and from emulator_status which reads state. However, 'neutral/released' is a bit ambiguous without context on what that means in emulator terms.

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?

Implies usage: stepping the emulator forward in time. But gives no guidance on when to use this vs emulator_run_scenario or run_pair_scenario, and no indication of what 'neutral/released frames' means practically or when stepping is preferred.

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