mouse_click

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

With zero annotations, the description carries the full burden and delivers richly: the scaled-display pitfall, refusal via coordinates_off_screen instead of clamping to an edge, tab-raising behavior with and without session_id, the approval foregrounding side effect, and the activate_session='none' special case. This is unusually thorough behavioral disclosure for a pointer tool.

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?

Every sentence earns its place and the most critical fact (coordinate space) is front-loaded. However, five distinct topics are packed into a single unbroken paragraph, which slightly hurts scannability for an agent parsing the text.

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?

An output schema exists, so return values need no description. The genuinely complex facets — coordinate space, off-screen error behavior, session targeting, activation modes — are all covered. Small gaps remain: what null x/y means (both default to null) and what 'the quiet check' refers to, but neither blocks correct 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, and it largely does: x/y get their physical-pixel semantics, session_id gets its tab-raising role, and activate_session gets its special 'none' value. Button, clicks, and interval are left to their self-explanatory names and defaults, which is a minor gap given the zero-coverage 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 and resource: clicking on the real desktop at absolute virtual-desktop coordinates. Explicitly distinguishes itself from page_click by naming the coordinate-space difference (physical screen pixels vs viewport CSS pixels), so an agent can tell the two apart without opening either 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?

Names page_click as the alternative and the axis of differentiation (coordinate space, with devicePixelRatio scaling), giving an explicit when-not-to-use signal. Also provides concrete invocation guidance: pass the preferred session_id so the right tab is raised after the quiet check, and use activate_session='none' to click the desktop as-is.

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