mouse_click_at

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

With no annotations, the description still discloses two genuinely useful behavioral facts not present in the schema: the left-button default and the coordinate frame anchored to the last screenshot. It omits failure behavior (what happens if no screenshot exists or coords exceed the screen), any settle/timing behavior, and the meaning of hold_ms.

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?

A single sentence with no waste. The action and the coordinate frame are front-loaded, and the button default is attached inline where it is immediately relevant.

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 four-parameter input-synthesis tool with no annotations and no output schema, this is close to adequate: the core semantics of the action and its coordinate system are stated. The remaining gap is hold_ms and error/precondition behavior, which matter for reliable invocation.

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 does add real meaning for x/y (pixel coordinates of the most recent screenshot) and button (left by default), but hold_ms is left completely undefined in both schema and description, and there is no guidance on coordinate bounds versus screen size.

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 gives a specific compound action (move pointer to (x, y), then click) and pins the coordinate frame to 'the most recent screenshot'. That clearly separates it in spirit from mouse_move_to (move only) and mouse_click (click at current position), though it never names those siblings explicitly.

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: an agent must infer this is the atomic move-then-click primitive and that it is preferable to chaining mouse_move_to + mouse_click. There is no explicit when-to-use, when-not, or statement of prerequisites such as having taken a screenshot first.

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