Desktop Press

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

With no annotations, the description carries the full behavioral burden and leaves key questions unanswered: which window or application receives the keystroke, whether a window must be focused first, and whether the action is repeatable or has side effects. The unexplained 'headed' flag is not addressed at all, so an agent cannot reason about execution context.

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?

The description is a single front-loaded sentence with an immediately useful parenthetical of examples, and no wasted words. Its brevity is the right call, though it borders on thin for a tool with an unlabeled parameter.

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 explained. However, for a low-complexity tool with 0% schema coverage, the definition omits the target-window/focus context and the meaning of 'headed', both of which an agent needs to call it 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 description coverage is 0%, so the description must compensate. It does add useful meaning for 'key_combo' by showing format examples ('ctrl+c', 'return', 'escape', 'tab'), but the 'headed' boolean receives no explanation anywhere, leaving half the surface undocumented.

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 gives a specific verb and resource ('send a keyboard shortcut or key combo') and concrete examples of accepted values. It is clear what the tool does, but it never distinguishes itself from nearby siblings such as desktop_type (typing text) or desktop_action, leaving the agent to infer the boundary.

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?

Usage is only implied: the agent can guess this is for key combos rather than literal text, but the description never states when to prefer it over desktop_type or desktop_click, nor any prerequisite such as a focused window. No explicit when-to-use or when-not-to-use guidance is present.

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