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

Annotations only give the generic profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds the far more important behavioral fact that the call has no immediate effect on the shop and instead produces a preview plus a confirmation link that only the merchant can act on. That deferred-application model is exactly the kind of context annotations cannot convey.

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, front-loaded with the resource and immediately followed by the most decision-relevant fact (no immediate change). The minor-units sentence is a slight tangent for a tool whose inputs are currency codes and rates, keeping it just short of a 5.

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 no output schema, the description carries the return-value burden and does so by describing the preview and confirmation link, plus the actor who can apply the change. It leaves open what the preview contains and whether repeated calls accumulate pending changes, but nothing essential to correct invocation is missing.

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% — rounding, currencies and fixedRates are each documented in detail in the schema — so the baseline is 3. The description adds only 'Money is integer minor units (cents)', which is loosely tied to fixedRates and arguably ambiguous given the schema's example rate of 1.10.

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 — which currencies shoppers can read prices in — which is unique among the settings_* siblings (settings_tax, settings_language, settings_store_defaults all cover different resources). It also immediately discloses the twist that the call sets up a change rather than applying it, so the agent knows exactly what this tool is.

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 workflow ('returns a preview ... a confirmation link. Only the merchant, on that page, can make it happen'), which implies when to reach for this tool, but it never names an alternative or states an explicit when/when-not condition against siblings like settings_store_defaults or settings_details. Usage is inferable rather than spelled out.

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