Play a gesture

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

Annotations already declare a non-read-only, non-idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the tick granularity (1/50 s), the hard constraint 'At most 5 s of waits in total', and the atomic one-request nature of the gesture. It stops short of saying which window receives input or what happens when the wait budget is exceeded, which keeps it from a 5.

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 purpose and the exactness rationale are front-loaded, then the grammar is enumerated in a compact inline list, then the exclusion is placed last. Every clause carries either a verb, a constraint, or syntax; nothing is redundant with the title or schema.

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 mutation tool with no output schema and only two parameters, the description covers intent, syntax, timing, and limits adequately. The remaining gap is outcome behavior — no mention of what is returned, whether a failed step aborts the sequence, or which window receives the synthesized events — which matters for a non-idempotent input injector.

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 100%, so 'gap' and 'steps' are already documented at a basic level; the baseline would be 3. The description earns above that by supplying the step grammar ('move X Y', 'click [X Y]', 'down [X Y]' plus right/middle modifiers, 'wait N') and clarifying that 'wait N' means N additional ticks, which the schema's 'the steps, in order' does not convey. It never explicitly ties the tick unit back to the 'gap' parameter, so it is not quite complete.

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?

States a specific verb and resource ('Play a sequence of mouse and keyboard events in one request') plus the timing model ('timed on the Amiga in ticks of 1/50 s'). It also names the sibling tools it competes with ('the separate mouse and key tools'), so an agent can tell it apart from amiga_mouse, amiga_key_press, and amiga_drag without opening those schemas.

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 an explicit positive condition ('for gestures that must be exact: a fast drag, a key chord, a burst of typing') and an explicit negative one ('For single actions the separate mouse and key tools are simpler'). That is a clear when-to-use / when-not-to-use routing rule naming the alternatives.

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