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

Annotations already carry the full safety profile (readOnly, idempotent, non-destructive, open-world), so the description's job is to add scope context — which it does by asserting the fetch works against *any* flow, matching the openWorldHint. It does not describe error behavior on malformed keys or response volume, which keeps it short of a 5.

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?

Definition is front-loaded, followed by key syntax, then examples, then sibling routing — four compact sentences with no filler. Every sentence carries either a semantics rule or a routing decision.

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?

Covers usage, key syntax, flow discovery, and alternatives for a 5-parameter read tool. The remaining gap is return shape — there is no output schema here, so the description could say what comes back (series metadata plus observations) and how last_n interacts with start/end_period.

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%, so baseline is 3, but the description adds real meaning: it explains that key positions are dot-separated dimensions and that empty positions wildcard, plus concrete worked examples (key="B.USD.NOK.SP" for daily USD→NOK spot). This goes beyond the schema's one-line field notes.

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 ("Generic SDMX data fetch from any Norges Bank flow") and scopes it precisely as flow-agnostic series retrieval. It explicitly separates itself from get_policy_rate and points to list_flows, so an agent can distinguish it from the related siblings without opening a schema.

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?

Names two alternatives and the conditions that select them: use get_policy_rate for the policy rate specifically, and list_flows to discover valid flow references. It also warns against guessing an IR key, which is an explicit when-not.

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