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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: the data source (cube snboffzisa, series LZ, monthly) and the domain constraint that the SNB uses a single target value with no corridor since the 2022 redesign. It does not state freshness or update cadence beyond 'monthly'.

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 tight sentences, front-loaded with the return contents before provenance and the domain caveat. Every sentence adds distinct value and there is no redundancy or filler.

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 and no parameters, the description carries the full burden and does describe the returned fields (current rate, effective date, previous rate, its effective date, decision history). It omits specifics like units, precision, or data freshness, but it is complete enough for an agent to call the tool correctly.

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?

The tool takes zero parameters, so per the rubric the baseline is 4. There is no parameter surface for the description to clarify.

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?

Names a specific resource (the SNB policy rate) and enumerates exactly what it returns: rate, effective date, previous rate and its effective date, plus decision history. It also differentiates itself from the get_cube sibling by noting it is computed rather than raw observations, so an agent can select it confidently.

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?

It effectively routes the agent away from get_cube for this data ('rather than left for the caller to infer a decision date from get_cube's raw observations'), which is clear when-to-use guidance. There is no explicit when-not-to-use or statement of preconditions, but the alternative is named and the selection condition is implied.

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