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

It adds real context beyond the annotations: the call is a no-op preview, it returns a confirmation link, and only the merchant on that page can actually flip the storefront. One caveat keeps it from a 5: 'Calling this changes nothing' reads as read-only, which sits in tension with readOnlyHint=false (a confirmation artifact is presumably created); read supportively, the sentence is disclosing that the mutation happens off-tool, not contradicting the annotation.

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?

Purpose is correctly front-loaded and the preview/confirmation explanation is tight, but the middle sentence about money in cents earns nothing in this tool and invites the agent to look for monetary parameters that do not exist. Roughly one of four sentences is wasted.

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?

With one boolean parameter, no output schema, and annotations covering the safety profile, the description supplies what is missing: that the call is a preview returning a confirmation link, and that a human completes the change. It does not mention how to inspect the current open/closed state (shop_state), which is the main remaining gap.

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 100% and the single 'online' parameter already documents both branches (demo becomes paid shop, password comes off, coming-soon page, nothing deleted) in more detail than the description does. The only parameter-adjacent sentence in the description, about money in integer minor units, is off-topic for a shop-open/close tool, so the baseline 3 applies with a small noise penalty rather than any added value.

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 first sentence gives a concrete verb pair (open / take offline) on a concrete resource (the shop/storefront), so an agent immediately knows this is a state-toggling tool and cannot confuse it with reads like shop_state or with unrelated siblings like storefront_set_password. The scope is stated without jargon and needs no schema inspection to understand.

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 explains the two-step affordance (preview then merchant confirmation) but never states when to reach for this versus alternatives such as shop_state for checking current status, nor any precondition for calling it. Usage is implied rather than guided, so 3 is the honest level.

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