adb_screenshot

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

With no annotations provided, the description must disclose behavioral traits itself. It explains the optional device parameter and auto-selection behavior, and states that it returns the screen image. However, it does not clarify the output format (e.g., binary data, file path) or potential error cases (e.g., multiple devices without specifying one). This leaves some ambiguity about side effects and return semantics.

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 concise and well-structured, leading with the core action and then providing purpose and parameter details. The Args section is clearly labeled. It avoids unnecessary verbosity, though the purpose line could be integrated more tightly with the action line. Overall, it is efficient and easy to scan.

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 a single optional parameter and no output schema, the description covers the primary functionality and usage. However, it lacks details about the return value's representation (e.g., is it a base64 string, a file path?) and does not mention failure modes (e.g., no devices connected, multiple devices without a specified device). These gaps could leave an agent unsure how to consume the result or handle edge cases.

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 single parameter 'device' is fully explained: it is the serial number, and the description covers the default behavior when omitted (auto-selects if only one device). This adds significant meaning beyond the schema, which only provides type information. Since schema description coverage is 0%, the description fully compensates for the parameter.

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 the Android device screen as a screenshot.' It specifies the resource (Android device) and the outcome (screen image for visual inspection). The mention of 'Android' distinguishes it from sibling tools like sim_screenshot (iOS simulator) and screenshot_app, providing implicit differentiation.

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 provides explicit guidance on when to use the tool: 'Use this to see what's currently displayed on the device.' It does not explicitly mention alternatives or when not to use it, but the 'Android device' qualifier implicitly differentiates from similar screenshot tools. It could be improved by naming alternative tools for other platforms, but the current guidance is clear enough.

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