Observe Screen (Screenshot + UI Tree)

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description does not need to repeat these. The description adds that the tool returns both screenshot (base64) and UI tree, which is useful behavioral context. No contradictions with 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?

The description is a single, efficient sentence that contains all essential information: the tool's action and when to use it. No extraneous words or redundancy.

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 read-only tool with annotations, the description adequately covers the return values (screenshot base64 and UI tree). However, it does not specify the format of the UI tree (likely XML), which could be helpful. Given no output schema, this is a minor gap.

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 sole parameter max_elements is fully described in the schema (type, default, min, max). The description does not add any additional meaning beyond what the schema provides. With 100% schema coverage, baseline 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 captures both screenshot (base64) and UI tree in one call, distinguishing it from sibling tools like adb_screenshot (screenshot only) and adb_ui_tree (UI tree only). The phrase 'Recommended for looking at the screen' reinforces the specific use case.

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 explicitly recommends the tool for 'looking' at the screen, implying it is the preferred choice when both screenshot and UI tree are needed. However, it does not explicitly mention when to use alternatives like adb_screenshot or adb_ui_tree individually, leaving some implicit guidance.

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