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

Annotations declare readOnlyHint=false and destructiveHint=false but say nothing about the two-step preview/handoff model; the description supplies that entirely — no prices are actually modified by the call, a preview plus confirmation link is returned, and the merchant must confirm out-of-band. This is exactly the kind of behavior-changing context the annotations cannot convey. The only gap is that idempotentHint=false is not addressed (whether calling twice yields two previews).

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?

Four short sentences, each carrying a distinct fact: what it does, the unit convention, the no-op behavior, and who can commit. The most surprising and decision-relevant fact (it's only a preview) is placed early and stated unambiguously.

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?

There is no output schema, and the description usefully covers the return value (preview of changes + confirmation link), so an agent knows what comes back. Combined with the annotations' safety hints and a fairly self-documenting nested schema, only minor details (preview expiry, behavior on repeated calls, max 500 products) are left uncovered.

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 50% and the description's one parameter-relevant sentence ("Money is integer minor units (cents)") largely restates what the schema already documents for change.value. It adds no explanation of the filter fields (productIds/collectionId/tag/vendor) or the percent/amount/set semantics, leaning entirely on the schema. Baseline 3 is appropriate given the schema does most of the work.

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 ("Change prices in bulk") that is clearly distinct from single-product editing siblings like products_edit. It does not explicitly name a sibling to route away from, but the bulk scope alone is distinguishing.

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?

"Calling this changes nothing: it returns a preview of what would change and a confirmation link. Only the merchant, on that page, can make it happen" tells the agent exactly how this tool fits in the workflow and where its authority ends, which is critical guidance. What's missing is an explicit alternative for small/single edits (products_edit) or a note on when bulk editing is preferable to editing individually.

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