vroid_current_screen

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

With no annotations, the description carries the full burden. It discloses that the tool is 'cheap-ish' (only OCRs the top strip, ~2 s) and that 'unknown' indicates a modal, which are useful behavioral traits. However, it does not explicitly state that the tool is read-only or has no side effects. For a diagnostic tool, this is a minor omission, so a 4 is appropriate.

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 compact and well-structured: the first sentence states the primary purpose, and the second provides usage guidance and troubleshooting. Every sentence contributes meaningful information without redundancy. The 'unknown' tip is an efficient way to add depth.

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 zero-parameter diagnostic tool, the description is complete. It covers purpose, possible outputs, cost, common failure interpretation, and a recommended next step. The output schema likely provides the exact return type, but the description already gives enough to the agent. No significant gaps remain.

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 has zero parameters, so the baseline is 4. The description adds value by enumerating the possible output values (the five screen states), which helps the agent interpret the result. No parameter details are needed, so this dimension is well-served.

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 tool's purpose: to identify which VRoid screen is on top, listing the possible outputs (start, editor, export_vrm, hair_editor, unknown). The verb 'identify' and the resource 'screen state' are specific, and the explicit list of possible values distinguishes it from sibling tools that perform actions rather than diagnostics.

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 explicitly says when to use it: 'worth calling whenever a flow tool fails' and explains the common failure mode. It also provides guidance on interpreting the 'unknown' result (modal is up) and suggests a follow-up action (take a full-window screenshot). This gives clear decision-making context.

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