State-Tool

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

With no annotations provided, the description carries the burden of explaining behavior. It discloses the tool's read-style behavior by describing what it returns, including device context and interactive element details, and explains the effect of enabling use_vision. It does not explicitly state that it has no side effects, but 'Get current screen state' strongly implies a non-mutating read operation.

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 three sentences with no filler. It front-loads the core purpose, then provides return-value context, parameter guidance, and usage sequencing. Every sentence adds necessary information.

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?

For a simple one-parameter tool with no annotations and no output schema, the description covers the essential bases: what the tool does, what it returns, how to use the parameter, and when to invoke it. Nothing critical is missing for an agent to call this tool correctly.

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 provides no description for use_vision, only a boolean type and default. The description compensates by explaining that setting use_vision=True produces an annotated screenshot, which gives the agent actionable meaning for the sole parameter. This is sufficient for a single boolean parameter.

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 specifies the verb 'Get' and the resource 'current screen state', listing concrete outputs such as interactive UI elements, label indices, types, names, and tap coordinates. It also distinguishes itself from interaction-focused sibling tools by explicitly stating it should be called first before any interaction.

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 gives explicit usage guidance: 'Always call this first before interacting' and explains when to set use_vision=True for an annotated screenshot. It does not name alternatives or describe explicit when-not scenarios, but the sequencing instruction makes the intended context clear.

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