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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real value: data provenance (derived from the daily policy-rate series) and a concrete enumeration of returned fields, which matters since there is no output schema. No auth, freshness-lag, or revision caveats beyond that.

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?

Front-loaded with the definition of the rate and what the response contains, then the parameter. Slight redundancy in repeating the `history` default/max already in the schema, but no wasted sentences overall.

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 responsibly enumerates the return fields and explains how the value is derived, which is enough to call and interpret a one-optional-param read tool. Only minor gaps remain, such as units (percent) and the source/revision policy for the underlying series.

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% and the description's clause on `history` ('default 5, max 20') restates the schema verbatim, adding no new meaning. Baseline 3 applies since the schema does all the work for the single optional parameter.

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+resource ('Norges Bank's current key policy rate', glossed as the sight deposit rate) and enumerates exactly what is returned: rate, effective date, previous rate, prior effective date, decision history. This cleanly separates it from siblings like get_exchange_rate and get_series.

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 provenance note ('computed from the daily policy-rate series, so it reflects the most recent rate-setting meeting') implies when this beats the generic get_series, but it never names an alternative or states when not to use it. Usage is inferable rather than explicit.

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