mouse_click

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

With no annotations, the description carries the burden well on the most non-obvious trait: this drives the real OS pointer, not a synthetic DOM event, and in browser mode it moves the real pointer first before clicking in the viewport. That is material side-effect disclosure an agent could not infer from the schema. It stops short of stating behavior when x/y are null (presumably click at the current position) or any failure/timeout behavior.

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?

Three short sentences, zero filler, with the core action and the pointer type front-loaded and the sibling routing pushed to the end. Each sentence adds distinct information: what it does, how modes differ, where to go instead.

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?

The output schema covers return values and there are no annotations, so the description's job is mode/coordinate semantics and sibling routing, both of which it handles for a five-parameter mutation tool. The remaining hole is that button and double_click are undocumented in both description and schema, which for a click tool is a notable but not fatal gap.

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 0%, so the description must compensate. It adds real meaning for x/y by assigning them coordinate spaces (global screen coordinates in desktop mode, controlled-tab viewport in browser mode) and implies the mode enum. However, 'button' and 'double_click' are never mentioned, leaving two of five parameters documented nowhere.

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 verb+resource ('Click the real desktop pointer') and immediately delimits the two operating modes, including the coordinate space each uses. It explicitly names two sibling tools (smart_click, handle_popup) with the conditions that select them, so an agent can route without opening any schema.

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 names the alternatives and their selection criteria: smart_click for semantic targets, handle_popup for an explicit consent choice, and a hard requirement that browser mode needs x/y in the tab viewport. What is missing is guidance on when NOT to use this at all (e.g. preferring smart_click for anything addressable) and what happens when coordinates are omitted.

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