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

The annotations (readOnlyHint false, destructiveHint false, idempotentHint false) already sketch the safety profile, and the description adds genuinely new behavioral context: the call is non-mutating, returns a preview of the diff plus a confirmation link, and requires human confirmation before anything happens. This two-step disclosure is exactly the kind of trait annotations cannot express; there is a mild tension with readOnlyHint=false but the description is clarifying rather than contradicting.

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?

Three short sentences, front-loaded with the action, then the units convention, then the critical preview/confirmation caveat. No wasted words and the most important behavioral fact is placed last for emphasis.

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 17 params at full schema coverage and no output schema, the description's job is to cover the behavioral gap, which it does by explaining the preview/confirmation return. It could say more about what the preview contains, but the essential calling context is present.

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 each of the 17 parameters is already documented in detail, so the schema carries the load. The description only restates the money-units convention ('integer minor units (cents)'), which the value parameter already explains, adding little beyond it.

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 a promotion's terms'), which is clear enough to separate it from promotions_delete and promotions_state. However, it does not explicitly differentiate itself from the closer sibling promotions_set_active, so the agent must infer the boundary.

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 conveys the workflow context (calling it produces a preview plus a confirmation link, and only the merchant can commit), which implicitly tells the agent this is not the final action. But it names no alternatives or exclusions, so an agent cannot tell from the text alone why it would pick this over promotions_set_active or discounts_coupon.

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