send_keys

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

Annotations only include destructiveHint: false (non-destructive). The description adds significant behavioral context: it simulates real OS-level key events, requires window focus, and cannot target specific elements. This goes beyond the annotation, openly disclosing limitations and behavior. No contradictions found. The high bar for transparency is met, though no return format or error conditions are described, which keeps it from a 5.

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 extremely concise: three sentences, each packed with essential information. The first sentence states the action types, the second explains the behavioral constraint (focus requirement), and the third lists example use cases. No redundant words, 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?

Given the tool has no output schema and 2 parameters with full schema coverage, the description is well-matched. It explains the core mechanics, constraints, and typical use cases. It does not detail error scenarios or real-world caveats (e.g., special character handling beyond unicode), but for a simple input tool, this is sufficient. Lacks only a note on return value (maybe null or success flag), but not critical.

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 100%, so baseline is 3. The description adds meaning by explaining the action types (pause, text, virtual key code) and notes that 'down: true/false' controls key press/release behavior, which the schema's description for 'down' is limited. It also mentions Unicode support in text, complementing the forceUnicode parameter. This lifts the score to 4.

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 sends keyboard input, specifying three action types (pause, text, virtual key code). It also distinguishes from sibling tools that target elements or windows, by explicitly noting it sends keys to whatever window has focus, not a specific element. This makes the purpose specific and differentiates from other tools.

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 context for when to use this tool: for key combos, navigation keys, or typing into controls without addressable elements. It explicitly says the target must be focused and cannot target a specific element. However, it does not mention when not to use it (e.g., when an element is addressable, use click_element or set_value instead), so it loses a point for lacking explicit alternatives or exclusions.

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