emulator_screenshot

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description states it returns a path but doesn't disclose critical behavioral details: where the screenshot is saved, in what format, behavior if the target is not running/connected, whether the file is overwritten if it already exists, or whether file naming collisions are handled. For a tool that writes files to disk, this is a meaningful transparency gap.

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 efficient sentence with zero filler words. Every word earns its place. It's appropriately front-loaded with the action verb 'Save'. It could be argued it errs on the side of being too terse rather than over-verbose, which is the better failure mode for conciseness.

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 the parameter coverage is 0%, there are no annotations, and no output schema exists, the description is under-specified for the tool's complexity. The tool writes a file (implying filesystem side effects) and has two parameters whose semantics are opaque. With sibling tools like gb_gpu_snapshot existing, the description should clarify how a screenshot differs from a GPU snapshot. This description is adequate for a trivial tool but lacks needed behavioral and parametric context.

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 0%, so the description must compensate, but it provides essentially no parameter information. The two parameters (name, target) are only documented by their schema titles and defaults. The description mentions 'for a target' which hints at the target parameter's role, and 'return its path' hints that name may generate the filename, but these are implicit and marginal. A dedicated sentence explaining name and target would add value beyond the bare 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 states a clear verb+resource: 'Save a screenshot for a target and return its path.' It clearly describes the action (save screenshot) and the scope (for a target). It distinguishes reasonably from siblings, which cover other emulator operations (status, step, tap, etc.), though the sibling bizhawk_screenshot exists but the description doesn't differentiate between emulator vs bizhawk implementations beyond the tool naming convention.

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?

There is no guidance on when to use this tool versus alternatives. It doesn't mention that there are alternative screenshot tools (bizhawk_screenshot, gb_gpu_snapshot) or when one might be preferred over another. The description gives no context about prerequisites (e.g., emulator must be running) or when capturing a screenshot is appropriate.

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