browser_hover

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

No annotations exist, yet the description discloses the key behavioral traits: the pointer motion is native, no click occurs, and the action 'may take desktop focus' — a real side effect an agent must know about. It also states the target must be fresh, visible and enabled, which implies stale refs fail, though it doesn't say what error results.

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?

Three short sentences, no filler, and the primary action is front-loaded with the side-effect warning and follow-up step after it. Every clause carries information.

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 one-param, no-annotation, no-output-schema tool, this covers action, side effects, target preconditions, and the recommended next step (re-snapshot). Only the failure mode for stale/invisible refs is left unspecified.

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% — the only parameter is an undescribed 'Ref' string. The description compensates by defining the required precondition ('fresh visible enabled reference'), telling the agent the ref must come from a current snapshot and target an actionable element, which is meaning the schema does not carry.

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 (move the native pointer over a reference) and immediately disambiguates from the sibling browser_click by saying 'without clicking'. The agent can tell exactly what operation runs 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?

'Read a new snapshot for revealed menus' gives a clear use context — hovering to expose hover-only UI — and 'without clicking' implicitly routes to browser_click when activation is wanted. No explicit when-not or prerequisites, so it stops short of a 5.

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