press_keys

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

With no annotations, the description carries the full burden, and it does add real behavioral context: keys map to US physical positions, repeat sends the combination N times, and hold_ms keeps keys depressed. It omits what happens on unrecognized key names, whether input targets the focused window, whether an active session is required, and any error behavior.

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 core action and input format, then one compact line per optional parameter, each earning its place with a concrete example. No filler, no restatement of the tool name.

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, and the parameter semantics are fully covered. The remaining gap is environmental context, such as focus/session requirements and invalid-key handling, which would round out a no-annotation tool but is not essential for correct invocation.

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, and it documents all three parameters: keys with a format example list, repeat with its multiplier semantics and a boot-menu example, and hold_ms with its timing purpose and a POST example. That is full semantic coverage of every parameter.

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 (press) and resource (key/key combination) and illustrates the input vocabulary with concrete examples ('ctrl+alt+delete', 'super+r', 'shift+tab') that implicitly separate it from type_text and click. It does not name a sibling tool explicitly, so differentiation is inferential rather than stated.

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 context is embedded in the parameter notes ('down x5 in a boot menu', 'hold F12 during POST'), which gives the agent realistic scenarios for repeat and hold_ms. There is no explicit guidance on when to choose this over type_text or click, so routing must be inferred from the key-name examples.

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