drag

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered structurally. The description adds the useful distinction that coordinates are screenshot- or window-relative, but stays silent on the confirmation workflow, reversibility, and any side effects of a drag on the target app.

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?

A single front-loaded sentence with zero filler. It is efficient, though arguably terse for a 10-parameter tool with a confirmation workflow that goes unmentioned.

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?

Parameter documentation and annotations are rich, and no output schema is needed. The missing piece is behavioral context around the required confirmation_token for high-risk drags and how this tool relates to left_click_drag, which matters for correct invocation.

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 both coordinates, duration, app selector, and coordinate_space are fully documented in the schema itself. The description only loosely ties 'screenshot/window-relative coordinate' to the coordinate_space enum, adding no syntax or format detail beyond the schema baseline.

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?

Specific verb (drag) plus resource (coordinates) with scope clarification that both start and end points are involved. However, it does not distinguish itself from the highly similar sibling left_click_drag, leaving the agent to guess which of the two drag tools to invoke.

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?

No when-to-use guidance, no exclusions, and no mention of when this differs from left_click_drag or hover. It also fails to state that a confirmation_token may be required before a high-risk drag.

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