Inspect screen

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

No annotations are present, so the description must carry the safety and behavior burden. It conveys a read-only fetch via the verb 'Get' and mentions 'stable element ids', but it does not disclose limitations such as whether only visible elements are included, whether the hierarchy may be stale, or any accessibility prerequisites.

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 two sentences with the core function first and actionable consumption instructions second. Every word serves a purpose; no redundancy or filler.

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?

With no output schema, the description explains the output type (compact JSON), key fields (id, text/resource-id), and how to use it with act tools. It could be more explicit about what elements are included (e.g., visible vs. hidden), but it is sufficient for a typical agent to correctly invoke and interpret the tool.

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% description coverage for the single device_id parameter, including format and source. The tool description adds no parameter-specific information, 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 'Get the current screen's view hierarchy as compact JSON with stable element ids', which is a specific verb and resource. It also distinguishes from screenshot-based inspection by saying 'never retype from a screenshot', positioning itself as the source for textual and structural data.

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 direct usage guidance: 'Use the id field with act tools (tap/input_text/...)' and 'Copy text verbatim'. It clearly tells the agent when this tool's output is needed, though it does not explicitly contrast with find_elements/find_text or take_screenshot for when to prefer those alternatives.

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