Right-click

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

Annotations already communicate that this is non-readonly and destructive, so the description is not required to repeat that. It adds useful behavior beyond annotations: the pointer is treated the same as for click, and the expected follow-up workflow is described.

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?

Four compact sentences, all relevant, with the core purpose first. There is no filler or repetition, and each sentence earns its place.

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 an action-only tool with no output schema, the description is complete: it states what the action does, how to coordinate with get_app_state, when to choose click instead, and how to supply coordinates. The agent has enough to invoke it 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?

Schema coverage is 100%, so the baseline is 3, but the description adds explicit mutual-exclusion guidance ('Pass element_id or x and y, not both') and clarifies that coordinates refer to screen positions. This adds value beyond the schema descriptions.

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 ('Right-click ... to open its context menu') with the resource ('an element or screen position'). It also explicitly differentiates from the sibling click ('Use click for normal activation'), so an agent can distinguish when to use each.

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?

It gives a clear workflow: right-click, then use get_app_state to read the menu, then click an item. It also names the alternative for normal activation and gives an exclusion rule ('Pass element_id or x and y, not both').

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