sequence

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

With no annotations provided, the description carries the full burden, and it does so thoroughly. It discloses ordering guarantees, failure semantics (a failing step stops the run and reports which one), the need for window= for reliable typing, opt-in stop_on_change behavior including its false-positive caveat, and the `then` observation options. This goes well beyond a basic statement of what the tool does.

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 dense but every sentence earns its place: the core purpose is front-loaded, the example makes the schema concrete, and each caveat (error stopping, window focusing, stop_on_change tradeoffs, then-coverage) is necessary for correct use. It is long only because the tool is genuinely nuanced.

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?

This is a composite tool with meaningful behavioral nuance, yet the description covers all three parameters, the valid step ops, failure/cancellation semantics, observation modes, and common pitfalls. Since an output schema exists, not describing return values in prose is acceptable. Nothing essential for an agent to decide whether and how to call it is missing.

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, and it fully does. It defines the steps array with an exact JSON shape and example, explains the op enum, clarifies `window=` semantics, and explicitly names `stop_on_change` and `then` with their defaults and behavior. Every parameter is given meaning beyond its schema title.

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 a specific verb-resource pair: 'Run an ordered list of actions in ONE call', and distinguishes sequence from single-action siblings by emphasizing that multiple steps can be batched into one round-trip. It also names the supported step types (pointer, keyboard, click_ui, hypr, wait_for), making its role 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 description gives clear context: use sequence when you need an ordered micro-sequence of actions like click/type/enter, and it explains the round-trip benefit over issuing several calls. It does not explicitly state when not to use it or name alternatives by name, but the 'vs several calls' framing effectively implies the alternative.

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