click

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only names the interaction modes and coordinates; it does not disclose side effects, no-op behavior, frame handling, or what happens after a click. The schema's partial hint about 'suspected_noop' and autoClimb is not mirrored in the description, leaving important runtime behavior undocumented.

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 pipe-separated structure is compact and front-loads the primary use case ('Interact by ref: click'). However, the description is visibly truncated with 'vie…', which harms completeness. Conciseness is good, but structure is marred by the incomplete ending.

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?

With 9 parameters, no output schema, and no annotations, the description should provide enough context for correct invocation across modes, coordinates, frames, and edge cases. It covers ref-based click/hover/rightclick/drag but omits coordinate semantics, button behavior, frameId, and autoClimb. The tool is callable in simple cases but under-specified for the full range of supported inputs.

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 description adds useful semantics for drag (fromRef→toRef) and clarifies that mode defaults to click, complementing the schema's sparse enum. However, x/y is truncated ('x,y vie…') and its meaning is left ambiguous, and button, frameId, and autoClimb are not addressed beyond the schema. With schema coverage at 56%, the description only partially compensates for the undocumented parameters.

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 an explicit action—'Interact by ref'—and enumerates the main modes: click, hover, rightclick, and drag, which makes the tool's core purpose clear. It also explains the drag variant with fromRef→toRef. However, it does not differentiate this from sibling interaction tools like press_key, type_text, or form, so it stops short of a 5.

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 lists modes but provides no guidance on when to choose click versus hover versus rightclick, nor when to use this tool instead of siblings like press_key or type_text. There are no exclusions, preconditions, or context cues for when this tool is the appropriate choice.

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