describe_screen

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

With no annotations supplied, the description carries the full disclosure burden and does well by enumerating the returned content, including extra diagnostics (overlaps, clipped text, off-screen elements) that an agent would not otherwise anticipate. It stops short of saying whether the call is read-only, whether it refreshes the view, or what the latency/format of the result is.

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?

One tightly packed sentence with the core output front-loaded and the supporting detail (positions, tap-centers, layout problems) following. The closing 'No image' is a useful delimiter with no wasted words.

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?

The tool is a parameterless reader with no output schema, so the description must convey the return shape, which it does by itemizing the element attributes and diagnostics. Minor gap: it does not describe the overall output structure or how layout problems are reported.

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 tool takes zero parameters, so the description has no parameter semantics to add and cannot misrepresent any. Baseline score applies.

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 states precisely what the tool produces: a text outline of the current screen covering every text, input, image and pressable with position, size and tap-center. The phrase 'No image' implicitly distinguishes it from screenshot-style siblings, though no sibling is named explicitly.

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?

Usage is only implied: an agent can infer this is the inspection step before clicking, typing or scrolling. There is no explicit guidance on when to prefer it over refresh_screen or use_target, nor any note about whether it re-reads the screen or returns a cached outline.

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