sequence

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

With no annotations provided, the description carries the full burden. It discloses the total duration cap of 60 seconds, that a step with no inputs acts as a pause, and that everything is released at the end. This is strong behavioral context, though it doesn't mention error handling or whether steps are atomic.

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?

Extremely concise and well-structured: an opening sentence, a precise step schema definition, and two critical behavioral notes in short sentences. No wasted words.

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 tool with no annotations, 2 parameters (one undocumented), and no output schema, the description provides most of what's needed to invoke it correctly: step format, duration cap, and release semantics. The omission of 'snapshot_after_ms' is a gap.

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 0%, so the description must explain parameters. It provides detailed step field semantics (buttons array, axis ranges -1..1, trigger ranges 0..1, duration_ms) and notes that no inputs means a pause. However, the second parameter 'snapshot_after_ms' is not mentioned at all.

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 it runs timed states in order and releases everything, distinguishing it from single-input siblings like press or hold. It also defines the step structure explicitly.

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 implies usage for multi-step timed input sequences but does not explicitly state when to use this over chaining individual tools or how it compares to the 'hold' or 'play_recording' siblings. Some guidance implied by the step format.

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