element_pick

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

Annotations are neutral (not read-only, not destructive). The description adds context: it starts a UI overlay, waits for a click, returns selector, DOM, style, and bounding-box facts. It does not contradict annotations and goes beyond them by explaining the interactive nature.

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 two sentences, no wasted words. It front-loads the main action and purpose, then adds details about return values and constraints.

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?

With 4 parameters (1 required), no output schema, and neutral annotations, the description adequately explains what the tool does and returns. It could mention timeout or cancellation behavior, but the return facts list provides sufficient context.

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 well-documented. The description adds no additional param details beyond the schema, so a baseline score of 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 the verb (start or cancel) and the resource (in-page human element picker overlay). It mentions returning specific facts and distinguishes from sibling tools by noting it does not persist skills, which sets it apart from skill-related tools.

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 implies usage for picking elements interactively and notes it does not persist skills, suggesting when not to use it. However, it does not explicitly state when to use this tool versus alternatives like inspect or query_dom.

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