ui_dump

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

With no annotations, the description carries the full behavioral burden, and it delivers: it lists exactly what fields each element includes, explains the state-flag legend ([C]lickable/[T]ext-mezo/[E]nabled/[S]elected), states that center coordinates are provided, and describes the only_interactive filtering effect. It also implicitly signals a read-only inspection behavior via 'uiautomator'.

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 dense but efficient: three sentences cover purpose, output content, downstream tool integration, alternative routing, and parameter behavior. No sentence is wasted, and the core purpose is front-loaded before the field-level detail.

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?

An output schema exists, so the detailed field listing is a bonus rather than a requirement. The description covers how the returned id connects to tap_element/type_into, the filtering parameter, and when to choose a simpler sibling. It is missing only a brief mention of serial and a comparison to the screen-observation siblings (screenshot/ocr_screen/observe_screen), which keeps it from being fully 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?

The schema has 0% description coverage, so the prose must compensate. It does explain only_interactive=True: only clickable/editable elements are shown, producing a shorter response. However, the serial parameter is never mentioned, leaving one of the two parameters without any semantic guidance in either the schema or the description.

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 opens with a specific function: 'Az aktualis kepernyo UI-elemeinek strukturalt listaja' (a structured list of the current screen's UI elements), naming the resource and the verb. It also differentiates itself from siblings by explaining that it provides the IDs and coordinates that 'tap_element'/'type_into' consume, and explicitly mentions 'tap_element'/'find_element' as alternatives.

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?

It gives concrete routing advice: ui_dump is 'a legmegbizhatobb modja' (the most reliable way) for the model to know where to tap, but 'meg egyszerubb kozvetlenul a tap_element/find_element tool-t hasznalni' (simpler to directly use tap_element/find_element). It does not compare against other screen-reading siblings like screenshot, ocr_screen, or observe_screen, so the guidance is clear but incomplete.

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