send_keys

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that this drives a real Chrome browser via the OctoLimb extension and warns about OS-specific shortcut differences, but it omits where the keys land (focused element? page body?), what happens on failure, and any side effects such as page navigation from Enter.

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 purpose and examples are front-loaded and earn their place, but 'This gets used in keyboard press' is filler restating the name, and the closing OS warning is vague rather than actionable. The bracketed preamble is boilerplate shared across a tool family.

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 two-parameter real-browser action tool with no annotations and no output schema, the description covers purpose and key format but leaves target-focus behavior, failure modes, and the intent parameter unexplained. Adequate to call it, thin for calling 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 coverage is 100%, so baseline is 3, but the description goes beyond the terse 'keys to send' schema text by giving concrete syntax examples ('Control+o', 'Control+Shift+T') that define the expected key-string format. The second parameter (intent) is never mentioned, which keeps this from a 5.

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+resource ('send strings of special keys') and enumerates examples (Backspace, Insert, Control+o), so the agent knows this is keyboard-event injection rather than text entry. It only implicitly distinguishes itself from the sibling input_text, which types characters into fields.

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 bracketed preamble gives a real routing condition ('use only when the task requires acting on a real website'), which is genuinely useful for choosing this over a non-browser path. However, it never says when to prefer send_keys over input_text or execute_js for keyboard work, leaving the sibling choice to inference.

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