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

Annotations only declare read-only/idempotent/open-world; the description adds the substantive behavior an agent cannot get from them: data freshness (roughly twice-daily snapshots), per-list caveats (Canada entity-only, Australia pending), the exact error string for an unknown or removed id ('entry_not_listed'), and what 'proof' accompanies each record (official file URL, SHA-256, source date). The free-tier/quota rules are also spelled out, including that errors do not count.

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?

The first three sentences are well front-loaded and earn their place, but the closing metering paragraph runs long on prepaid-credit policy, unmetered routes, and empty-answer billing edge cases — details relevant to cost but disproportionate to a two-parameter lookup. Trimmed to the free-answer cap and the 'error names the HTTP alternative' rule, the definition would be markedly tighter.

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?

For a two-parameter read with no output schema, the description covers the input contract, list coverage gaps, return shape (names, aliases, programmes, countries, first_seen, last_changed, proof), the failure case, and freshness. An agent has everything needed to call it correctly and to interpret an empty or error result.

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 the baseline is 3, but the description still adds meaning the schema lacks: it characterizes the id as the listing's own id with cross-list examples ('RUS0849 on uk or 36 on ofac-sdn') and flags that 'au' is not loaded yet, which the bare enum does not reveal. The one-to-40-character constraint is already in the schema, so it is repeated rather than additive.

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 and resource ('Returns one current entry ... by list and exact id') plus the source coverage (US, UK, EU, Canada entity-only, Australia not loaded). It explicitly separates itself from sanctions_search_entries (name matching) and sanctions_list_changes (removal reasoning), so an agent can pick it without opening either 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?

Gives an explicit entry condition — 'Use it after sanctions_search_entries or sanctions_list_changes gave you an id' — and names the correct alternative for the adjacent jobs (name matching, change history). It also states the limits of the data (monitoring feed, snapshots refreshed about twice a day, not a real-time clearance decision), which tells the agent when not to rely on it.

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