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

Goes meaningfully beyond the annotations: it discloses a per-call token cost ("호출마다 토큰 1소진"), that the call creates an XBOSS job and persists results, that secrets are never passed through MCP input, and that despite querying the institution this is not a pure read. Those are exactly the side-effect details readOnlyHint=false and destructiveHint=false cannot convey. It still omits anything about session lifetime or return payload.

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 critical instruction is correctly front-loaded, but the body is bloated and mixes Korean and English mid-paragraph. Lines like "This optional key is not available to anonymous taste calls" read as template leakage with no bearing on this tool, costing space that could have explained the session result.

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 session-establishing, non-read-only tool with no output schema, the description covers ordering, how credentials are handled, token cost, and the job-creation side effect. What it does not cover — what the session handle looks like or how long it survives — is the main remaining gap for a login tool.

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 3 is the floor, but the description genuinely adds semantics for request_idempotency_key: generate and save it before the first request, reuse it only with identical arguments to recover a lost response, and use a fresh key for a new execution. It also warns that a provider-specific idempotency_key is a different field, heading off a likely confusion. account_link_id is left to the schema, which already documents it well.

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 a specific verb and resource ("NH농협은행 빠른조회 세션을 기존 연동으로 만듭니다" — create a fast-inquiry session over an existing linkage) and distinguishes itself from siblings with "Call this FIRST before any other tool for this provider." A caveat: the middle section drifts into idempotency mechanics, which dilutes but does not obscure the core purpose.

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?

"Call this FIRST before any other tool for this provider" gives an explicit ordering rule that matters for a session tool. The idempotency guidance also states when to reuse vs. mint a new key. It does not name any alternative tool or describe a when-not case, keeping it short of a 5.

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