dump_ui

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

The description adds 'via the accessibility tree', which is meaningful behavioral detail beyond the annotations (readOnlyHint, idempotentHint, destructiveHint). It explains the source of data, which helps the agent understand potential limitations or permissions. 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 succinct sentence that front-loads the purpose and key details. Every word is informative, with no 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?

Given the presence of an output schema and the tool's read-only nature, the description adequately explains what is returned and the method. However, it could be improved by mentioning output structure or usage scenarios. Still, it's largely complete for a basic inspection 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 sole parameter 'device_id' is not explained in the description. With 0% schema description coverage, the description should compensate but fails to add any meaning beyond the schema field name. This leaves the agent unclear about what device IDs are valid or how to obtain them.

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 verb 'Get' and the resource 'all UI elements on screen', listing specific attributes (text, resource-id, class, bounds, clickable). This distinguishes it from sibling tools like screenshot (image capture) or find_element (search for specific element).

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 when you need all UI elements on screen, but does not explicitly state when not to use it or suggest alternatives like find_element or screen_summary. The context is clear but no exclusion criteria are provided.

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