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

Annotations already declare it non-read-only, non-idempotent, open-world, and destructive; the description adds genuinely useful context beyond that: it emits a real event, leaves the button held until pointer_up, and may change application state. It is consistent with destructiveHint=true but does not describe e.g. coordinate defaults or failure behavior, so 4 rather than 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?

Two sentences, front-loaded with the trigger condition, then the key behavioral fact (held until pointer_up). No filler or restatement of the name.

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 low-param, output-schema-backed mutation tool with full annotation coverage, the description supplies the essential coordination semantics (must be paired with pointer_up) and the state-change warning. It omits the required-device prerequisite and any note on how x/y absence behaves, minor gaps given the schema already covers them.

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 x, y, button, device, and backend are all documented in the schema already. The description adds no syntax, default, or backend-selection guidance beyond what is in the schema, so the baseline 3 is appropriate.

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 states a specific verb and resource (press and hold a mouse button / pointer-button-down event) and scopes it to native desktop drag or selection gestures on a paired computer, distinguishing it from browser_click, ui_click, and pointer_click. An agent can tell this is the 'press' half of a press-and-release pair without opening the schema.

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?

It gives a clear trigger condition ('when the user asks to press and hold ... to begin a drag or selection gesture') and names the gesture family it belongs to. It does not explicitly name pointer_up as the required follow-up tool or call out when pointer_click is preferable, so the routing guidance stops just short of 5.

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