cyd_key_press

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

With no annotations, the description carries the burden of explaining behavior, and it does well: it says the key behaves like a hardware keyboard press, reaches the editor/app, and that CTRL+C interrupts a running app. It also clarifies machine-specific (cyd), modifier syntax, and the accepted key set. It does not cover return values or failure modes, but the most important side effects are disclosed.

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 compact and front-loaded with the tool's purpose, followed by a dense but understandable list of valid keys. The only minor noise is the cryptic 'Action, L0' fragment, which adds little for an agent; otherwise every sentence earns its place.

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 one-parameter action with no output schema, the description covers what the tool affects (the editor and running app), the accepted key grammar, and an important side effect (CTRL+C interruption). It is nearly complete, though it does not state what the tool returns or how an agent would detect a failed key press.

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 fully explain the sole 'key' parameter. It does so by enumerating characters, named keys, function keys, and modifier prefixes with a concrete example (CTRL+S) and a special-case behavior (CTRL+C interrupt). This goes well beyond the raw regular expression and makes correct invocation predictable.

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 uses a specific verb and resource: 'Press one key as a hardware keyboard would.' It clearly separates this from text input or touch input by focusing on a single key event and enumerating valid key names. This lets an agent distinguish it from siblings like cyd_type_text and cyd_tap.

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 description provides useful usage context: the editor receives the key, a running app reads it via cyd.key(), and CTRL+C has the special effect of interrupting a running app. It does not explicitly name alternatives or state when not to use this tool, but the single-key framing makes the intended boundary reasonably clear.

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