glass_gesture

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

With no annotations, the description carries the full transparency burden. It discloses timing behavior (all pointers down at t=0, up at duration_ms), the meaning of a held pointer (from==to), and a potential failure mode (Unsupported error on backends lacking multi-touch). This is solid behavioral context, though it does not state whether the tool blocks until completion or what it returns on success.

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 two sentences long and every clause earns its place. The first sentence packs the core action, parameter constraints, and timing model; the second covers both gesture recipes and a platform limitation. It is front-loaded with the most important information and avoids redundancy.

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 output schema and no annotations, the description covers the essential aspects: what it does, how to construct gestures, parameter constraints, and a known error condition. It does not describe the return value or success/failure signaling, but that is less critical for an imperative gesture tool; overall, it is sufficient for an agent to invoke it correctly.

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 the baseline is 3. The description adds value by translating the raw schema fields into gesture semantics: pinch = two pointers toward/apart, rotate = two on an arc, swipe = parallel segments, and held finger = from==to. This goes beyond the schema's individual property descriptions and helps the agent encode higher-level intents.

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+resource combination: 'Perform a multi-touch gesture' and immediately details the semantics (2–10 pointers, straight from→to segments, window-relative px). It clearly distinguishes itself from sibling single-pointer tools like glass_click, glass_drag, and glass_move by focusing exclusively on multi-touch interactions.

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 provides clear context on when to use the tool by enumerating common multi-touch gestures (pinch, rotate, two-finger swipe) and even explains how to construct them with pointers. It does not explicitly name alternative tools for single-touch actions, but the examples make the intended use obvious, and the note about backend support adds a practical usage caveat.

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