desktop_action

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

No annotations exist, so the description carries the full burden. It usefully discloses the coordinate reference frame (full desktop screenshot) and the foreground-window requirement, plus warns that dialogs and OS permissions 'may need local handling' — implying the call can stall or fail outside the agent's control. It does not state that these actions are irreversible desktop mutations, what happens on timeout, or whether the call waits for UI settling, which are material gaps for a blind click tool.

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-loaded with the capability list, then constraints, then caveats — the right ordering for an agent scanning for fit. Four short lines with no filler; the only weakness is that the fragments are terse enough that some (like 'keys/text') double as both action names and parameter names, creating minor ambiguity.

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?

An output schema exists, so return values need not be described. Still, for a six-parameter, unannotated, mutating GUI tool, the description should specify per-action parameter requirements and failure behavior; it instead leaves the agent to guess how to drive scroll amount, key chords, and text entry correctly.

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 partially does: the action list effectively enumerates valid action strings, and 'Coordinates use the full desktop screenshot' pins down x/y semantics. But 'amount' (presumably scroll magnitude) and the format of 'keys' (list of key names? chord syntax?) are never explained, nor which parameters each action requires — a significant residual gap at 6 undocumented params.

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 names the resource ('Visual GUI interaction') and enumerates the concrete operations: click, double_click, right_click, move, drag, scroll, keys, text. An agent can tell this is low-level desktop input simulation rather than a native/API-level action. It stops short of naming a sibling, but the verb+resource pairing is specific enough to act on.

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?

'Inspect screenshots before/after' and 'OrcaSlicer must be foreground' give a workflow hint and a precondition, which is more than nothing. However, with many native_* siblings (native_transform, native_text, native_scene_read) that likely accomplish the same goals more safely, the description never says when GUI clicking is the right choice versus those alternatives, nor when to call desktop_focus or desktop_screenshot first.

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