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

Beyond readOnlyHint=true it discloses that no credential/login is required, that reads hit stored records only, and that each call consumes a token (호출마다 토큰 1소진) — quota information annotations cannot express. The extended idempotency-key lifecycle paragraph adds real behavioral context, though 'Without it, calling again remains a new request' restates the point rather than adding detail.

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?

Purpose and scope are front-loaded in the first two sentences, and every subsequent paragraph is relevant. The idempotency block runs three sentences where two would do, and the trailing '사업자 유형: 개인사업자 호출마다 토큰 1소진' line is terse and untranslated, making it easy to miss.

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 carries return-value burden and does describe the key fields each entry contains. For a single-optional-parameter read tool with annotations covering safety, this is nearly complete; only the exact shape of the returned list (pagination, other fields) is left implicit.

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 goes well beyond the one-line schema field: it says to generate and save the key before the first request, to reuse it only for lost-response recovery with identical arguments, to use a fresh key for a new execution, and that it is unavailable to anonymous calls. It also warns not to confuse it with a provider-specific idempotency_key.

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 ('List the Shinhan Bank account links this caller registered') and names the exact payload it returns (account_link_id, bank_account_credential_id). It also explicitly contrasts itself with shinhan_easy.accounts.list, so an agent can distinguish the two without opening the 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?

The description makes the tool's role clear: it supplies the ids that the accounts and transaction history tools require, and it distinguishes cached-our-records from live-bank fetching by naming the alternative. It stops short of an explicit 'call this first, then use accounts.list' sequence, leaving the ordering implied.

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