Locate element (fusion)

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

No annotations are provided, so the description carries the full burden, and it does substantial work: it discloses the resolution strategy (structured first, vision fallback), the snapping behavior, and the coordinate space of results. It omits whether the call is read-only/side-effect-free and any auth or performance caveats, which keeps it from a 5.

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?

Three dense sentences, zero filler, and the core identification plus the most decision-relevant behavior (fallback order) is front-loaded. Every sentence carries distinct 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?

With no output schema, the description steps in to explain the return coordinate space, which is the key thing an agent needs to pass results to computer_action. It is nearly complete, missing only target-selection guidance for the nested object and explicit read-only confirmation.

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 50%, so the description must compensate, and it only partially does: it explains the instruction/descriptor duality and the result coordinate space, but says nothing about the target block (platform, deviceId, cdpEndpoint) or preferStructured, which are the exact fields left undocumented in 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 ('Find an element') and clarifies the two input modes (natural language vs structured descriptor). It also hints at its relationship to computer_action, though it does not explicitly differentiate itself from siblings like computer_inspect or computer_get_state.

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?

Gives clear context: structured lookup is attempted first with vision grounding as fallback, and it names computer_action as the downstream consumer of the result. No explicit 'when not to use this' or named alternative for locating-only scenarios, so it stops short of a 5.

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