Send Text Input

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

Annotations already flag readOnlyHint=false and idempotentHint=false; the description goes beyond those flags by explaining the mechanism — repeated calls append to the focused field — which is precisely the behavioral nuance structured hints cannot convey. The focus prerequisite is also a real runtime condition worth stating. Minor omission: the failure mode when no field is focused is not described.

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?

Four sentences, each with a distinct job: core action, precondition, mutation semantics, and alternative routing. No filler or repetition of schema content, and the most decision-relevant facts are front-loaded in the first sentence.

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 tool with no output schema, the description covers the action, the focus precondition, the append/mutation behavior, and when to choose it over keypress. The only gap is error behavior (e.g., what happens if nothing is focused or input is rejected), which is a minor omission for a simple input-send tool.

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 both text and device are already documented with examples and default behavior. The description adds only the 'literal' nuance to the text parameter, which is marginal beyond the schema's 'Text to send.' The baseline 3 for high schema coverage applies.

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 opens with a specific verb and resource — 'Type a literal text string into whatever input field is currently focused on the device' — anchored to the ECP /input endpoint. It also preemptively distinguishes itself from keypress, its nearest sibling, so an agent can route correctly without opening the schema. The domain is completely unambiguous.

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 precondition is stated explicitly ('Requires a text field to already be focused'), the alternative tool to satisfy it is named ('use keypress to navigate into one first'), and the substitution rule is given ('Use this instead of sending characters as individual keypress keys'). Both when-to-use and when-not-to-use are covered with zero inference required.

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