Take 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. It only states 'Capture a PNG screenshot' without disclosing how the screenshot is returned (e.g., base64, file path), whether it is saved, or any device state requirements. This is a significant transparency gap for a tool with no output schema.

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, front-loaded sentence with no redundant words. It conveys the essential action and output format efficiently, earning a perfect score 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?

The tool is simple (one parameter, no output schema), but the description lacks important context about what the agent will receive after invoking the tool. Without an output schema, the description should mention the return format or behavior. The description is adequate but incomplete for an agent to fully understand the tool's outcome.

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 100% coverage for the single parameter (device_id) with a detailed description including examples. The tool description does not add parameter-level meaning, but the schema already provides sufficient semantics, so the baseline score of 3 is appropriate.

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 tool's function: 'Capture a PNG screenshot of the current device screen.' It uses a specific verb ('Capture'), defines the resource ('current device screen'), and specifies the output format (PNG). This differentiates it from sibling tools like inspect_screen (UI hierarchy) and start_recording (video).

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 for capturing a screenshot, but provides no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives like inspect_screen or note any prerequisites. The context is clear but the guidance is only implicit.

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