bizhawk_frame_advance

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

No annotations provided, so description carries full burden. It explains behavior: does not change pause state, works whether paused or running, scales linearly (~16ms per frame plus round-trip), and returns error if core doesn't support frameadvance. Also notes RAM behavior after reset.

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?

Well-structured with labelled sections (PURPOSE, USAGE, BEHAVIOR, RETURNS). Every sentence is informative with zero wasted words. Highly efficient and scannable.

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 a single parameter with full schema coverage and no output schema, the description covers purpose, usage, edge cases (error if core unsupported), performance characteristics, and return format. Nothing missing.

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?

Only one parameter 'count' with 100% schema coverage. Description adds latency scaling and new framecount formula beyond schema's min and default. Provides practical context: 'New framecount = previous framecount + count.'

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 'Step emulation by exactly N frames' and returns framecount. It distinguishes from siblings like pause/unpause, reset, and save/load state by focusing on frame-precise stepping.

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?

Explicitly tells when to use (frame-precise automation, animation inspection, after reset) and when not to (prefer save/load state for long jumps). Also suggests combining with press_buttons and notes initialization after hard reset.

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