find

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

Annotations already establish readOnlyHint=true and openWorldHint=true, so the safety profile is covered. However, the description adds no behavioral disclosure beyond those annotations—there is no mention of return values, scoping (e.g., shared vs. default session behavior), pagination, or what happens when nothing matches. It adds only a list of selector kinds, which is more purpose than behavior.

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 a single efficient sentence that front-loads the tool's purpose and the supported selector kinds. Every word contributes value; there is no filler, and it remains scannable and information-dense without being overly terse.

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?

The tool has no output schema, and the description fails to explain what a successful 'locate' operation returns (an element reference? a locator token?), which is needed for downstream chaining with click/fill/expect. While the schema covers parameters and annotations cover safety, the description is not complete enough for an agent to confidently use the result of this tool; combined with the absent usage guidance, this is a notable gap.

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 100%, so the schema already documents the parameters thoroughly, including the enum-like values for kind and the nuanced behavior of lease and session. The description's mention of semantic strategies (text/label/placeholder/role/...) adds a lightweight overview but no new meaning beyond what the schema already provides, so the 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 states a specific verb ('locate') on a clear resource ('elements') and enumerates the supported semantic strategies, making the tool's function recognizable at a glance. It does not explicitly contrast itself with sibling tools like vision_find or candidates, so it stops short of full differentiation, but the description is unambiguous about WHAT it does.

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 no guidance on when to use find versus alternatives such as vision_find, observe, or candidates, nor does it state any exclusions or prerequisites. It merely restates the tool's own mechanism (semantic strategy) without providing context on when this tool is the right choice among the many sibling locator and inspection tools.

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