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

Beyond the readOnlyHint annotation, the description discloses the auth prerequisite (same account_link_id session), the retry semantics of the idempotency key (reuse only to recover a lost response; otherwise a new request), and a per-call quota cost ("호출마다 토큰 1소진"). These are exactly the operational facts annotations cannot convey, though the "anonymous taste calls" sentence is garbled and its meaning is unclear.

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?

Front-loading the session prerequisite is good, but the idempotency explanation sprawls across four sentences with repetition ("Without it, calling again remains a new request"), plus an opaque "anonymous taste calls" clause and a trailing Korean token note. It is serviceable but noticeably padded for a search tool.

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?

Auth, idempotency, and quota are covered, but with eight optional filter parameters and no output schema, the description says nothing about what the search returns (notice rows? counts?) or how paging works, and it omits the detail/select sibling relationship. Adequate for calling it, incomplete for using the result.

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 and the other seven parameters are already well documented. The description goes beyond that for request_idempotency_key, explaining its lifecycle (generate before first request, reuse only for recovery, new key per execution) and warning that a provider-specific idempotency_key is a distinct field — real semantic value the schema's one-line description does not carry.

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 second sentence gives a specific verb and resource: "Search health insurance premium notices." It is clear what the tool retrieves, but it never distinguishes itself from close siblings such as nhis_edi__hr_payroll__premium_notices__detail or premium_notices__select, so an agent must infer the search-vs-detail split.

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?

"REQUIRES prior nhis_edi__session__login call with same account_link_id" is a genuine precondition, and the idempotency paragraph explains how to reuse or regenerate the key. However, there is no guidance on when to choose this tool over premium_notices__detail/__select, nor any exclusion criteria, leaving tool selection implicit.

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