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

The annotations flag a destructive, idempotent write, and the description adds the key mitigating context: existing records keep their own currencies, so the change is not retroactive. It also explains downstream effect (summaries, statistics, trend reports). It does not cover auth/permission needs or the fact that calling with no arguments is a no-op, keeping it out of 5 territory.

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?

Two tight sentences; the action and its targets come first, then the consequences. No filler, and the cross-tool reference is packed into the same sentence rather than a separate aside.

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?

An output schema exists so return values need no explanation, and both parameters are covered by the schema plus the description's downstream effects. The only gap is the absence of any note on omitted-parameter behavior (both are optional) for a mutation tool.

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% with enums documented, so the baseline is 3. The description goes beyond that by explaining what the currency parameter actually controls downstream and that it becomes the default for create_record, which the schema alone does not convey.

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 plus two named resources ('display currency', 'app language') and the 'or both' scope. That is enough to separate it from the many update_* siblings (update_record, update_category, update_payment_method), which each operate on a different resource.

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 makes the tool's domain obvious but never says when to reach for it versus alternatives, nor any preconditions (e.g., must a profile exist, can both fields be omitted). Usage is inferable from the field list rather than stated.

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