press_key

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

No annotations are provided, so the description carries the burden. It discloses meaningful behavior: special keys trigger keyCode/e.which listeners, printable chars dispatch char events without insertText, and modifier keys suppress char dispatch. This is genuinely informative. However, it doesn't mention what happens on failure (e.g., unfocused element), which keys are NOT supported, or the '移植' porting note which is context about the tool's origin, not 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?

The description packs a lot of behavior into a dense block. It's front-loaded with examples and covers essential info, but it's a wall of text without structural breaks. The '移植 browser-harness press_key' sentence at the end is a provenance note that adds little agent value. The descriptor '修饰键位:' mixes Chinese and code inline, making parsing harder.

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 2-param keyboard tool with no output schema and no annotations, the description covers the key semantics and modifier behavior well. However, it lacks edge-case disclosures: what if the target page uses keydown vs keypress, does it require an active focus, and how does it interact with the page's current state. The sibling type_text likely overlaps, and the boundary isn't explicitly defined, which matters for selection.

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% on the schema side, so description must compensate for 2 parameters. The description explains 'key' well (examples, special vs printable behavior) and covers 'modifiers' with the bitmask mapping (Alt=1 Ctrl=2 Meta=4 Shift=8). Both parameters are effectively documented, though the modifiers bitmask format is somewhat cryptic and could benefit from clearer examples like 'Ctrl+A = key:'a'+modifiers:2'.

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 clearly states the tool presses a keyboard key, with examples ('Enter', 'a'). It distinguishes special keys (using virtual key codes) from printable character keys (which dispatch char events). It's a specific verb+resource purpose, though it doesn't explicitly distinguish from the sibling type_text tool — the distinction is implied rather than named.

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 clear usage context: when to use for special keys vs printable chars, and that modifiers suppress char events (Ctrl+A goes to shortcuts). It explains behavioral nuance for different page types. However, it doesn't explicitly say 'use type_text for longer text input' or name alternatives, though the char-event/long-key distinction implies a boundary.

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