ui_describe

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

No annotations are supplied, so the description must carry the full behavioral burden. It usefully discloses the data provenance (Android-reported attributes only, no OCR/vision) and that a coverage line reports how much of the UI the OS actually named — a real caveat about output quality. It omits anything about permissions, whether the call is read-only in effect, latency, or what happens when max_controls truncates the list.

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?

Three sentences, front-loaded with the key distinction, then data source, then return shape. A portion of the third sentence enumerates return components that the output schema already covers, which is mild redundancy, but the framing sentence earns its 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?

An output schema exists, so the detailed return-value enumeration is largely redundant, while the genuinely undocumented area — the four input filters and how they narrow the result — is skipped entirely. For a tool whose whole value is targeted screen description, the filtering behavior should have been described.

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 description coverage is 0% across four parameters (role, region, max_controls, include_containers), so the description must compensate and does not — none of the four filters is mentioned or explained. The only hints are indirect ('ordered control list', 'include_containers' defaults), leaving the agent to guess valid role/region values and the meaning of the control cap.

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?

States a specific verb+resource and frames it decisively: 'Read the screen as CONTROLS, not pixels', with the data source spelled out (view class, resource-id, accessibility description, action flags, never OCR/vision). This immediately separates it from screenshot/vision-based siblings.

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?

'Prefer this over screenshots for understanding a screen' gives an explicit alternative and a selection condition. However, the sibling set contains many overlapping hierarchy/introspection tools (get_ui_tree, inspect_view_hierarchy, ui_snapshot, find_elements), and the description does not say when to choose this one over those.

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