adb_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. It conveys the tool is a read-only visual capture (clearly non-destructive by nature), which is somewhat implied by 'Capture the screen'. However, it doesn't disclose behavioral details like potential latency, whether it fails on locked/off screens, refresh timing, or that it returns a viewable image the agent can process — leaving some assumptions to the agent.

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?

A single sentence, zero waste, immediately front-loaded with the action and output format. Every word carries meaning. This is near-ideal 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?

The tool is simple (1 optional param, no output schema, read-only by nature), and the description adequately captures what it does. However, it could benefit from noting limitations (screenshot may fail or show blank on locked screens) or confirming the device must be powered on and unlocked. For a simple tool this is acceptable, but a small note on failure conditions would make it complete.

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 description coverage is 100% since the only parameter (serial) is fully described in the schema. The description adds nothing about the parameter, but the schema already documents 'device serial (host:port); omit if only one device', so a baseline 3 is appropriate given the schema does the heavy lifting.

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 uses a specific verb+resource ('Capture the screen as a PNG image') and clarifies the purpose is so the agent can SEE the device, distinguishing it from sibling tools that operate on device data (getprop, settings, logcat). It clearly communicates the visual-offload intent, though it doesn't explicitly name a sibling alternative like adb_screenrecord for video capture.

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 — capture the screen when you need visual context — but doesn't explicitly state when to use it vs alternatives. It doesn't mention exclusions (e.g., use adb_screenrecord for video) or context such as when screenshots fail (screen off, lockscreen). The intent is clear but not explicit about when-not-to-use.

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