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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false; the description adds real context on top: each call consumes a token, creates an XBOSS work item and persists a result, and it explicitly states the call is not pure read-only, which is consistent with the annotations. It also spells out retry/idempotency behavior (reuse the key only to recover a lost response, new key for a new execution). Some of the trailing text about '기관 데이터 변경은 도구별 실행 내용과…' is generic template filler rather than tool-specific behavior.

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 core message (log in first, returns success plus link ID) is front-loaded, which is good. But the body interleaves Korean and English, repeats the idempotency rule in several sentences, and carries boilerplate about XBOSS tasks and per-tool change procedures that does not help an agent decide or call correctly.

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 zero-required-parameter login tool with annotations and no output schema, it covers prerequisites (registered certificate), return values (success flag, account_link_id), ordering, cost, and retry semantics. What is missing is failure handling — expired or missing certificate, what a failed login returns — which matters for the one tool every other call depends on.

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 adds genuine meaning for request_idempotency_key beyond the schema's one-line gloss: when to reuse it, when to mint a new one, and that it is unavailable to anonymous calls. It also reinforces the 'one key per execution' rule and warns not to confuse it with a provider-specific idempotency_key. account_link_id is left entirely to the schema, which is acceptable given the full coverage.

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 ('등록한 공동인증서로 건강보험 EDI에 로그인해 세션을 만들고') and names what it returns (login success flag plus the account_link_id used). The 'Call this FIRST before any other tool for this provider' opener immediately separates it from the nhis_edi__session__status and downstream 조회 siblings.

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 explicit ordering ('Call this FIRST', '로그인이 필요한 건강보험 EDI 조회보다 먼저 부릅니다') that tells an agent exactly when to reach for it. It does not cover the inverse case — e.g. when a session already exists and the agent should check status instead of re-authenticating — so it stops short of full when/when-not/alternatives guidance.

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