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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true, so the mutation/non-idempotent profile is covered structurally. The description adds the environment scoping (desktop grid browser vs. real device) and concrete use-case targets, but says nothing about failure modes, whether hidden/offscreen sources are scrolled into view, or timing/intermediate hover steps that drag operations often need.

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 dense sentence with the primary action front-loaded and the disambiguation trailing. Every clause earns its place; the em-dash-heavy phrasing is slightly compressed but not padded.

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 three-parameter drag tool with no output schema, the definition supplies the environment, the disambiguation from sibling drag tools, and representative targets. Only failure/edge behavior is absent, which is a minor gap given annotations carry the safety profile.

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% — 'from' (CSS selector of element to drag), 'to' (CSS selector of drop target) and 'pageId' (from web_navigate) are all documented in the schema. The description only reinforces the pageId scoping, so it adds little beyond the schema and the baseline 3 applies.

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 (drag) and resource (element onto another) plus the operating context (DESKTOP grid browser, by pageId). It names its typical targets (reorderable lists, kanban columns, file drop targets), so an agent can distinguish it from device_drag_drop, ios_drag_drop and device_swipe without opening any 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?

Explicitly excludes the device case ('NOT a device — there is no webpage_drag') and routes to named alternatives (device_swipe / device_drag_drop for Android, ios_drag_drop for iOS) with the discriminating key ('by udid'). Both when-to-use and when-not-to-use are covered.

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