page_click

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses that the tab is not activated, the desktop cursor does not move, ambiguous or unreachable targets dispatch nothing, selector mode is hit-tested with auto-scroll, and coordinate mode is not hit-tested. It also reveals the 'obscured', 'occluded_by', and 'outside_viewport' result semantics. There is no annotation contradiction.

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?

The description is dense but logically organized: action first, then coordinate-space caveats, then behavioral guarantees. Every sentence carries a distinct operational fact and there is no filler. The long sentence structure could be easier to parse with bullets, but the information density justifies the length.

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 that an output schema exists and no annotations are present, the description covers the critical call semantics: target selection, coordinate systems, offsets, hit-testing, scrolling, and side effects. The only real gaps are generic parameter details like timeout units, button values, and the precise role of session_id in tab selection. For a complex 9-parameter tool with zero schema descriptions, this is close to complete but not entirely exhaustive.

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?

The schema has 0% description coverage, so the description must compensate. It does for the most confusing parameters: x/y are viewport-relative CSS pixels, offsets are measured from the element's top-left corner, an omitted offset axis uses the center, and selector accepts CSS or structured locators. Less critical parameters such as button, clicks, timeout, and session_id are left to their names and defaults, making the compensation strong but not exhaustive.

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 opens with a specific verb-resource pair: click a CSS/structured locator or viewport coordinates in a specific real browser tab. It also distinguishes itself from siblings by contrasting background CDP input with the physical screen pixels used by mouse_click and the device pixels used by capture_page_screenshot. The purpose is immediately recognizable and hard to confuse with alternatives.

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?

The description gives strong usage context: this is for in-page, viewport-relative clicking without activating the tab or moving the desktop cursor. It explicitly warns that mouse_click uses physical screen pixels and capture_page_screenshot uses device pixels, which tells the agent which coordinate spaces not to feed it. However, it does not provide a formal when-to-use/when-not-to-use decision rule beyond these coordinate caveats.

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