Computer Click

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

With no annotations, the description carries the full burden and does disclose a major behavioral trait: an outbound gate because a click can press Submit/Send/Delete, requiring a fresh CONSENT.txt. It also discloses that clicks:3 selects a line/paragraph, but says nothing about failure modes when no screenshot exists.

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 lines, front-loaded with the action and coordinate frame, then parameter meanings, then the gate. Every sentence carries information the agent needs; nothing is padded.

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?

Given an output schema exists and the description needn't explain returns, this covers action, coordinate space, all four parameters, and the safety gate. The main residual gap is what happens when there is no prior screenshot or how the gate failure is surfaced.

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, and it does: x/y are defined as pixel coordinates in the last screenshot, button is enumerated as left|right|middle, and clicks 1/2/3 is given concrete meaning including the triple-click text-selection case. Defaults and required-ness are left to the schema.

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?

States a specific verb+resource (click at x,y) and pins the coordinate reference frame to the LAST screenshot's pixel space, which separates it from drag/mouse_down_up style siblings. It doesn't name an alternative sibling explicitly, so it stops short of full sibling differentiation.

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?

Usage is only implied: the coordinate frame tells the agent it must screenshot first, and the CONSENT gate hints at when the tool is blocked. There is no explicit guidance on when to choose click over computer_mouse_down_up, computer_drag, or computer_type for a given interaction.

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