desktop_actions

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=false, so the danger profile is covered structurally. The description adds genuinely useful behavior beyond that: a hard cap of 50 steps and immediate abort via the user E-Stop at sub-millisecond latency. It says nothing, though, about what happens on a mid-sequence failure, whether partial side effects persist, or how deadline_ms interacts with the step loop.

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 sentences, both front-loaded with the essential fact (batched execution, hard abort) and no filler. The long parenthetical action list is dense but earns its place as the enumeration of what 'actions' means, though some of its entries duplicate the schema enum.

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 highly complex 19-parameter destructive batch tool with no output schema and near-zero schema documentation, the description covers execution model and the E-Stop abort but leaves failure semantics, verification/evidence options, and most tuning parameters unexplained. Adequate to start a call, insufficient to call it safely and correctly in edge cases.

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 19 parameters and only 5% schema description coverage, the schema does almost none of the explanatory work, and the description compensates only slightly by enumerating action values and the 50-step limit. Nothing is said about the high-impact knobs an agent must set correctly: deadline_ms, settle_ms, stability_ms, capture_after, evidence, expected_transitions, stop_on_window_change, require_window, or the nested verify/condition/region objects.

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 (Execute) and resource (a sequence of desktop actions) plus the 50-step bound and the action vocabulary, which is far more than a restatement of the name. It does not, however, distinguish itself from the many single-action siblings (desktop_click, desktop_type, desktop_drag), so an agent must infer that this is the batch/alternative-to-many-calls variant.

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 phrase 'in a single round trip' implies the intended usage is batching multiple actions to avoid per-call latency, but the description never states when to prefer this over single-action siblings or when not to use it. Usage is implied rather than prescribed.

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