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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description goes further by disclosing that each call consumes one token and creates/stores an XBOSS job, that the call is not purely read-only even when the source institution is not queried, and how idempotency keys behave on retry. The Korean passage ending in generic 'institution data changes follow each tool's procedure' is boilerplate, but the non-obvious cost and side-effect facts are exactly what an agent needs.

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 purpose and sibling distinction are front-loaded and efficient, but the body drifts into a long idempotency paragraph and an untranslated Korean block containing operational boilerplate about institution data changes. It is informative yet uneven in length and mixes two languages, which costs readability.

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 one-parameter list tool with no output schema, the description covers what is returned, the cost per call, the side effects, and the idempotency contract. The only shortfall is that the mixed-language tail adds ambiguity rather than information, but no essential invocation detail is missing.

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, and the description adds real meaning beyond it: the key is optional and authenticated-call-only, should be reused only to recover a lost response with identical arguments, is unavailable to anonymous calls, and must not be confused with a provider-specific idempotency_key. That is more than the schema's one-line field description conveys.

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: lists the Shinhan Bank account links this caller registered, and names the exact identifiers returned (account_link_id, bank_account_credential_id). It explicitly separates itself from sibling shinhan_easy.accounts.list, which fetches live accounts from the bank, so an agent can route correctly 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 clear context: no credential or login is needed, use this when reading stored links rather than live bank data, and generate request_idempotency_key before an authenticated first call, reusing it only for recovery. It does not state an explicit 'do not use when' case beyond the sibling comparison, but the selection guidance is actionable.

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