browser_locate

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

With no annotations, the description carries full burden. It details that coordinates are captured at call time and may be stale if page reflows. It also lists typed errors (BrowserNotConnected, ElementNotFound) with actionable steps, providing high transparency.

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?

Extremely concise and well-structured: first sentence states purpose, then alternatives, then caveats, then error cases. No wasted words.

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?

Despite no output schema, the description explains return coordinates and error handling. Could potentially detail the exact coordinate structure (e.g., {x,y}), but for an agent it's sufficient to know it returns coordinates compatible with mouse_click.

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 coverage is 100% with all parameters having descriptions. The description adds no additional meaning beyond the schema for parameters; it only provides context about selector being CSS and compatibility, which is already implied. Baseline 3 is appropriate.

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 clearly states it finds a DOM element by CSS selector and returns physical screen coordinates, and explicitly distinguishes itself from siblings like browser_click (find+click in one step) and browser_overview (discover selectors).

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?

Provides explicit when-to-prefer alternatives: 'Prefer browser_click to find+click in one step. Prefer browser_overview to discover selectors.' Also includes a caveat about stale coordinates after reflow.

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