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

Annotations only say readOnly=false and destructive=false, so the description carries real weight and delivers: a documented failure mode (multiple management numbers ⇒ login fails, no parameter can disambiguate) and an explicit per-call cost ("호출마다 토큰 1소진"). The idempotency paragraph adds recovery semantics but is partly verbose and the phrase "anonymous taste calls" is opaque jargon that doesn't land clearly.

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 most important instruction (call first, certificate login, uniqueness precondition) is front-loaded and the token cost is a single short clause. The idempotency section runs long with restatement ("Without it, calling again remains a new request") and ends on an unlabeled Korean fragment.

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 4-parameter login with annotations and no output schema, the description covers ordering, preconditions, cost, and retry semantics. It stops short of saying what a successful login yields (session lifetime/expiry) or that session state is inspected via the sibling status tool, which an agent must infer.

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; the description nonetheless adds meaning beyond the schema by tying business_registration_no to a uniqueness constraint against COMWEL management numbers. It also distinguishes request_idempotency_key from a provider-specific idempotency_key, a distinction the schema does not make.

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?

Names a specific verb (Login) and resource (COMWEL via NPKI AnySign certificate) and states the ordering constraint up front. An agent can tell it apart from comwel__auth__session__status, the only other comwel auth sibling, 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?

"Call this FIRST before any other tool for this provider" gives explicit sequencing, and the clause about business_registration_no mapping to exactly one management number states a hard precondition under which the call fails. It does not route the agent to comwel__auth__session__status for the already-logged-in case, so the when-not side is only partial.

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