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

Annotations already cover the read-only, idempotent, non-destructive profile, so the description correctly spends its budget on non-obvious behavior: an empty result before a UTXO set is published, plus the ordering of the returned cohorts. That is a genuine edge case an agent would otherwise not anticipate.

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 short sentences plus the REST endpoint line, front-loaded with the key fact and free of filler. The telegraphic phrasing ('Every URPD cohort once a UTXO set is published') is slightly elliptical but costs no length.

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 an output schema present, the description need not document return values, and annotations cover safety. What remains is the missing explicit link to get_urpd as the consumer of these cohort labels, which would make the discovery-tool role fully unambiguous.

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?

Zero parameters, so the schema baseline is 4. The description goes slightly beyond by enumerating example cohort labels (`all`, `sth`, `lth`, `age_under_1h`, ...), which helps the agent recognize the shape of values it will get back.

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?

The description names the resource unambiguously (URPD cohorts) and conveys that the tool enumerates the available cohort labels, including the ordering scheme (age aggregates first, then age bands youngest-first). It does not use an explicit verb like 'list', but the enumeration intent is clear and it reads differently from the data-returning siblings get_urpd / get_urpd_latest.

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?

Usage is only implied: an agent must infer that this is the discovery step to find valid cohort identifiers before calling get_urpd. The parenthetical '(none before)' hints at a precondition (no data until a UTXO set is published), but no sibling is named and there is no explicit when-to-use/when-not-to-use guidance.

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