as_adb_screenshot

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

Annotations indicate readOnlyHint=true and destructiveHint=false, and the description adds behavioral details: uses specific adb command, saves PNG on PC, requires workspace root and optional serial. No contradictions; additional context beyond annotations.

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?

Three sentences: purpose, args (summarized), returns. No fluff, front-loaded, easy to parse. Every sentence earns its place.

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?

Covers core functionality, inputs, and output. Does not detail error handling or edge cases (e.g., multiple devices), but for a simple read-only tool with an output schema, it is sufficiently 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 has detailed descriptions for each parameter, but the description adds valuable context: 'inside a workspace root' clarifies file location, and outlines return structure. With 0% schema coverage in the description, it still adds meaning beyond the schema.

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 device screen'), output format ('PNG'), and method ('adb exec-out screencap'). It distinguishes this tool from siblings like as_ui_screenshot or as_adb_shell by specifying it saves to the PC.

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 the basic usage context (input params, return value) but does not explicitly state when to use this tool over alternatives or when not to use it. The readOnlyHint annotation implies safety, but no direct guidance is given.

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