check_overlaps

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

With no annotations, the description carries the full burden and does well: it defines severity semantics (interactive=high, visual=low), states that parent-child overlap is normal and ignored, and describes the return payload (overlap pairs with bounds, overlap rectangle, area in px). It stops short of stating permission/auth needs or whether the operation is purely read-only, which is the remaining gap.

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?

Front-loads the one-line purpose, then uses two tight bullets for the modes and one closing sentence for the return shape. No filler; every sentence carries information.

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 4-parameter, no-required-arg detection tool with no output schema and no annotations, the description compensates well by documenting the return format and the overlap classification rules. It could still be more complete by declaring the read-only nature and any cost/pagination considerations.

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%, so the baseline is 3, but the bullets add real meaning to the 'mode' enum by explaining why interactive overlaps matter (unreliable clicks) versus visual ones, which the schema alone does not convey. The description does not add detail for screen, include_hidden, or min_overlap_area beyond the 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+resource ('Detect overlapping elements') and immediately scopes it to layout bugs and broken click targets. The two bullets further distinguish the internal interactive vs visual cases, so an agent knows exactly what this tool produces and can separate it from neighbors like inspect_element or find_element_at.

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 implied through the stated goal (finding layout bugs / unreliable clicks) and the severity framing, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many siblings. It leans on the reader to infer that this is the layout-validation tool.

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