emulator_run_pair_scenario

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. It reveals it does not do visual diffing, but does not disclose whether it writes files, mutates state, requires a running emulator, handles both GB and MD simultaneously, or what 'collect outputs' produces. Significant behavioral gaps for a tool that likely mutates emulator state.

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 concise sentence with zero waste. It's efficiently worded, though brevity borders on under-specification given the ambiguity of the tool's purpose.

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 tool with no annotations, no output schema, and 0% schema coverage on its only parameter, the description is markedly incomplete. The 1-parameter tool with no output schema and no safety annotations needs to explain the 'path' parameter, the return behavior, side effects, and prerequisites — none of which are addressed. Extreme simplicity of the schema could justify some leniency, but the 'paired scenarios' concept is opaque enough to warrant more explanation.

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?

With 0% schema coverage and a single 'path' parameter, the description must explain what the path refers to (scenario script file? emulator directory?). The description completely fails to clarify the meaning of 'path' — leaving the agent to guess whether it's a scenario file path, config path, or working directory.

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 the tool runs paired GB and MD scenarios and collects outputs without visual diffing. This is reasonably specific (verb=run, resource=paired GB/MD scenarios) and distinguishes from sibling emulator_run_scenario. However, it doesn't clarify why 'paired' is distinct or what 'collect outputs' means concretely, and the scope of the pairing could be clearer.

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 description mentions 'without visual diffing' which implicitly contrasts with sibling tools emulator_build_pair_diffs and emulator_build_pair_contact_sheet, but it does not explicitly say when to use this tool versus those alternatives, nor does it provide guidance on when paired execution is appropriate. No exclusions or alternatives are named.

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