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

Annotations only say readOnlyHint=false and openWorldHint=false; the description goes further by disclosing that each call consumes one token, that an XBOSS task is created and the result persisted, and that the call is explicitly not pure read-only regardless of whether the agency source is queried — consistent with the annotations. It also explains idempotency-key lifecycle (save before first request, reuse only for recovery, new key for new execution), which is real behavioral context. The Korean sentence encoding these side effects is awkwardly worded, which slightly reduces clarity.

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?

It is well front-loaded with the ordering rule and the core action, but the idempotency-key discussion runs four sentences and repeats itself, and the closing Korean block is dense boilerplate. The mix of English and Korean with no structure makes the reader do unnecessary parsing work for information that could be stated once.

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 login with no output schema, the description covers prerequisites and side effects but never states what the caller gets back — whether a session is now active for subsequent tools, how expiry or status is reported, or what a failed multi-mapping looks like. The 'call first' instruction implies session reuse, but the post-login outcome is left to inference.

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 already 100%, so the baseline is 3, but the description adds meaning the schema cannot: business_registration_no must resolve to exactly one COMWEL business management number or the call fails with no disambiguating input available. It also explains the request_idempotency_key lifecycle and warns that a provider-specific idempotency_key is a different field. account_link_id is only covered by the schema, not the description.

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 opening states a specific verb, resource and mechanism: login to COMWEL via NPKI AnySign certificate, and it is scoped to this provider so it separates cleanly from the other provider login tools in the sibling list. It does not explicitly distinguish itself from comwel__auth__session__status, and the later Korean boilerplate about XBOSS task creation muddies rather than sharpens the stated 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?

Strong explicit ordering guidance: 'Call this FIRST before any other tool for this provider.' It also states a concrete precondition for success — business_registration_no must map to exactly one business management number, and multi-mapping fails with no input able to disambiguate. It lacks an explicit when-not/alternative route (e.g., check session status first if already logged in), which keeps 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.