Drag

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

Annotations already indicate this is a mutating operation (readOnlyHint=false, idempotentHint=false). The description adds valuable behavioral context by stating the prerequisites: 'Requires admin mode AND MACCTL_ALLOW_INPUT=true, and the `cliclick` tool.' This informs the agent about environmental requirements and external dependencies. It also frames the action as human-style input simulation, which implies side effects on the target UI. No contradiction with annotations.

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 a single sentence that front-loads the core action and then adds necessary prerequisites. There is zero waste—every clause contributes either to the action definition or to operational requirements. It is concise and well-structured for quick comprehension.

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 tool with 4 required parameters and no output schema, the description covers the essential operational context: what the action is, its use cases, and its prerequisites. It does not explain the coordinate system (though schema says 'screen points') or potential side effects on the dragged object, but these are reasonably implied. The only minor gap is the lack of explicit statement about the result of the drag (e.g., no return value), but given no output schema, this is acceptable. Overall, it is sufficiently complete for an agent to decide when to invoke it.

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 100%: each parameter has a clear description (e.g., 'Start X (screen points).'). The tool description restates these coordinates in prose but does not add additional semantic meaning beyond what the schema provides. The baseline of 3 is appropriate since the schema fully documents the parameters; the description adds no extra parameter guidance.

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 a specific action: press at (x1,y1), move to (x2,y2), and release, explicitly calling it a 'human-style drag'. It lists concrete use cases (select text, move a window, drag a file), which distinguishes it from sibling tools like click, move_mouse, and type_text. The purpose is unambiguous and differentiates from alternatives.

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 provides clear context by naming the action and its typical uses (select text, move a window, drag a file). It does not explicitly state when not to use this tool or name alternatives, but the specificity of the drag action and the sibling list make the appropriate usage clear. A slight gap is the absence of explicit guidance about when to prefer this over click or move_mouse.

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