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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and the description corroborates that this is not a pure read ('순수 읽기 전용이 아닙니다') while explaining that each call consumes one token and creates an XBOSS job with stored results. That is useful beyond-schema context. It still does not explain session lifetime, whether repeated logins invalidate prior sessions, or what an agent should expect on failure, and the idempotency paragraph is generic boilerplate largely irrelevant to a login call.

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 sentence front-loads the critical ordering rule, which is good structure. The body is longer than needed for a two-parameter login tool, mixing Korean and English and including idempotency-recovery text whose purpose overlaps with the schema field description.

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-establishment tool with no output schema, the description covers prerequisites and safety profile reasonably but omits what the login returns (session handle, expiry) and how subsequent tools know the session is active. An agent has enough to invoke it but not to reason about session state afterward.

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% and both parameter descriptions are detailed, so the baseline is 3. The tool description adds that request_idempotency_key is optional, must be generated and saved before the first authenticated request, reused only for recovery, and is distinct from any provider-specific key — helpful framing beyond the schema, but the account_link_id semantics come entirely from the schema.

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 identifies a specific action and resource ('우리은행 빠른조회 세션을 기존 연동으로 만듭니다') and the 'Call this FIRST before any other tool for this provider' line distinguishes it from the sibling session/status and account-query tools. The purpose is clear but is buried under the ordering directive and idempotency boilerplate rather than front-loaded.

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?

Explicitly says to call this first before any other tool for this provider and that credentials are not supplied via MCP input, which gives an agent a clear precondition. It does not, however, name the status/logout sibling tools or state what to do if a session already exists, so the when-not guidance is incomplete.

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