take_screenshot

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

With no annotations provided, the description carries the full transparency burden. It discloses the side effect of writing to .dejank/artifacts and the underlying tools (adb/simctl), but does not explain overwrite behavior, device requirements, or return values. This is moderate transparency, sufficient for a simple screenshot operation but lacking deeper behavioral details.

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 that front-loads the core action and includes the destination. Every word carries meaning, with no filler or redundant information. It is exceptionally succinct and well-structured.

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 tool's simplicity (one parameter, no output schema), the description is mostly adequate: it states the purpose and output location. However, it omits any mention of return values (e.g., a file path), error conditions, or how the artifact can be accessed later. Sibling tools like list_artifacts imply retrieval, but the description does not explicitly connect these, leaving some contextual gaps.

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 input schema has zero description coverage, so the description must compensate for the platform parameter. It does not mention 'platform' or explain the meaning of 'auto' or the difference between android/ios, aside from implicitly hinting via adb/simctl. This is a clear gap, as the description adds little value beyond the enum values themselves.

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 the action (capture device screenshot) with specific implementation details (adb / simctl) and the output destination (to .dejank/artifacts). This distinguishes it from sibling tools that capture profiles or UI hierarchies, making the purpose immediately obvious.

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 implies usage when a screenshot is needed, but provides no explicit guidance on when to use this tool over alternatives such as get_ui_tree or tap. There is no mention of exclusions or prerequisites, so it offers only implied context rather than detailed when-to-use instructions.

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