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 transparently discloses the default behavior (bundled element list), the coordinate space (device-tap coord, no scaling), and the performance tradeoff (includeElements fetch adds a roundtrip). Could mention image format/resolution details, but what's disclosed is genuinely useful and actionable.

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 information-dense and every clause earns its place, but it runs slightly long (4-5 sentences) and front-loads the core purpose while pushing alternatives to the end. No filler or repetition—just detailed but not bloated. Minor deductions for length.

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 2-param tool with full schema coverage and no output schema, the description is complete: it explains default behavior, coordinate-space caveat, performance tradeoffs, when to use alternatives, and how to opt out of the bundled fetch. It compensates fully for the missing output schema by describing the return shape (JPEG + element list with bounds). No gaps remain.

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 coverage is 100% with both parameters (udid, includeElements) documented in the schema. The description adds context for includeElements beyond the schema ('Set false to save tokens on screens you only need to look at') which is valuable, but udid gains no additional meaning. Baseline 3 is appropriate given full schema coverage plus a small bonus from the includeElements context.

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?

Clear verb+resource ('Take a screenshot of a device') with specific detail: returns JPEG plus a labeled UI element list. Distinguishes from siblings like device_screen, android_mjpeg_screenshot, and ios_screenshot by explaining the bundled element list that eliminates a roundtrip to device_page_source. The description names sibling alternatives explicitly.

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?

Provides explicit when-to-use guidance: 'Prefer device_tap_by_text for elements with a visible label; use these bounds only as a fallback.' Also names android_video_stream as the alternative for continuous observation/debugging stuck flows, and explains when to set includeElements=false. This is model-tier usage guidance.

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