ACTION_INPUT_TEXT

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

With no annotations, the description carries the burden and does substantial work: it discloses the return value (input_success), that a11y mode reads back to verify content, the privilege requirement for shell/ime, the non-ASCII limitation, and the focus-reporting quirk. It does not say whether typed text replaces or appends to existing content, which is a meaningful behavioral gap for an input tool.

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?

Purpose and output are front-loaded, then caveats follow in a compact sequence. It is dense and mostly earns its sentences, though there is minor clutter such as a stray double period and a slightly run-on mode/parenthesis clause.

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 an 8-parameter, 3-mode action with no output schema, the description covers output name, verification behavior, platform prerequisites, non-ASCII limits, and interpolation. The main missing piece is the replace-vs-append semantics of the text parameter.

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 the schema already explains every parameter and the baseline is 3. The description adds a little (mode requirements, why target matters, ${var} interpolation applied to all string parameters) but mostly restates what the schema already documents.

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?

Opening clause gives a specific verb+resource (write text into an input box) plus the optional submit behavior, so the agent immediately knows what the tool does. It never names a sibling such as ACTION_CLICK or ACTION_TEXT_OPERATION to draw a boundary, so it stops short of full differentiation.

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?

Gives concrete selection guidance: use a11y mode for Chinese/non-ASCII, shell/ime only when Shizuku or root is available, and pass target coordinates for QQ/WeChat inputs that do not report focus. No explicit exclusions or named alternative tools are given, so it is clear context rather than a full when/when-not rule set.

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