Double Click

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

Annotations already flag the operation as destructive and non-read-only, so the safety profile is known. The description adds no further behavioral context, such as the possibility of triggering application actions or requesting an observed state afterward. It is behaviorally neutral and does not contradict the annotations.

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?

One short sentence with the action verb first and no filler. It is easy to scan and every word contributes to the core meaning. The terseness costs behavioral detail, but that is a completeness issue, not a conciseness one.

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 tool with five parameters, a union target type, and mutation semantics, the description alone is thin, but the input schema provides detailed field descriptions and annotations cover the destructive nature. What is still missing is high-level guidance on when a double-click is the correct interaction and what observable effect to expect. Overall it is minimally viable rather than fully complete.

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?

With schema coverage around 60% and detailed inline descriptions for target, strategy, modifiers, and return_state, the schema does most of the work. The description's 'bound element or frame coordinate' aligns with the target union but adds no new meaning beyond the schema. Baseline 3 is appropriate because the description neither compensates for app_ref nor repeats unnecessary schema details.

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 verb+object 'Double-click a bound element or frame coordinate' names a specific action and the two supported target kinds, and it distinguishes this tool from single/triple/right-click siblings. 'Bound element' is slightly jargon-y but understandable in context of the target schema. This goes well beyond a tautology.

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?

There is no guidance about when to use double_click instead of left_click, triple_click, or other click variants, and no mention of prerequisites or context. The description only states what the tool does, not when to prefer it. This is absence of guidance, not misleading guidance.

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