send_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 discloses key non-obvious behaviors: it does not submit, and it should not be used for passwords. This goes beyond the schema. However, it omits edge cases like what happens if no input field is focused, so it is not fully exhaustive but still strong.

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: three sentences covering purpose, non-submit behavior, and usage guidance, plus a one-line args description. Every sentence adds essential information, and the key behavioral points are front-loaded.

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?

The tool has an output schema, so return values are covered elsewhere. The description fully explains the tool's action and its place in the workflow (followed by send_enter/send_pf). It could mention error conditions or behavior without a focused field, but for a simple single-parameter typing tool, this is nearly complete.

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. The 'text' parameter is described only as 'Characters to type,' which is minimal but does convey its purpose. It lacks details about formatting, encoding, or special keys, but given the parameter's simplicity, this is adequate yet not rich.

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 explicitly states 'Type text into the current input field at the cursor position' with a specific verb and resource, and immediately clarifies 'Does NOT submit.' This clearly distinguishes it from sibling tools like send_enter and send_pf, leaving no ambiguity about its function.

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?

It provides direct instructions: 'Use send_enter / send_pf afterwards to submit' and explicitly warns 'Do NOT use for passwords; the login tool fetches them from the OS keychain.' This gives clear when-to-use and when-not-to-use guidance with specific alternatives.

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