Hover

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

Beyond the annotations (idempotentHint, destructiveHint, readOnlyHint), the description discloses platform-specific side effects: 'On macOS the user's own mouse pointer is not moved; on Windows and Linux it may be, and the result then says via cursor.' This is essential behavioral information that the annotations do not convey, giving the agent a precise expectation of OS differences and result messaging.

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 four sentences, front-loaded with the primary purpose, followed by observation steps, parameter constraint, and platform behavior. Every sentence adds necessary information with no fluff. It is appropriately sized for the tool's complexity.

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?

Given no required parameters and no output schema, the description covers the full workflow: what the tool does, what to do afterward to observe results, how to activate a found element, and platform-specific pointer behavior. An agent has enough information to call hover correctly and integrate it into a broader UI automation sequence.

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 each parameter is already documented. The description adds a critical constraint not present in the schema: 'Pass element_id or x and y, not both.' This clarifies mutual exclusivity and prevents misuse, going beyond the baseline of 3.

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 the tool's function: 'Move the agent pointer over an element or screen position without clicking, to reveal hover menus, toolbars, tooltips or drag handles.' This uses a specific verb (move), a clear resource (pointer/element/screen position), and a purpose (revealing UI elements). It also implicitly distinguishes hover from click and drag siblings by explicitly noting 'without clicking' and mentioning activation as a separate step.

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 practical guidance: 'Follow with get_app_state or screenshot to see what appeared' and 'Use click to activate.' It also states the parameter usage rule 'Pass element_id or x and y, not both.' It does not explicitly name alternative tools or when-not-to-use conditions, but the workflow guidance is clear and actionable enough to place it above a vague 3.

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