mac_drag

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

No annotations, so the description carries the full burden. It discloses a real behavioral trait — a 30s validity window and an element_no_longer_valid error on stale indices — which is valuable beyond the schema. It does not describe what a successful drag returns or any permission needs.

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?

Two tightly-packed sentences with zero waste; the core action is front-loaded and the precondition follows.

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 2-param, no-annotation, no-output-schema action tool, the description covers the action, input source, staleness window, and a specific error token. Only success behavior and return details are absent, which is minor.

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 0%, so the description must compensate. It does clarify where the integers come from (element indices from mac_ax_state) and their freshness requirement, which is genuinely useful, but adds no format, range, or failure behavior for the parameters themselves.

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 (drag) and resource (UI element to UI element) with concrete use cases (windows, sliders, selections). This implicitly distinguishes from mac_click (a click) and mac_scroll, but never names the alternative explicitly.

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 a concrete precondition and operational constraint: use from_index/to_index from the latest mac_ax_state, valid for 30s. No explicit when-not-to-use or named alternative tool guidance, so not a 5.

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