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

Annotations already declare readOnlyHint=true, so the description wisely spends its budget elsewhere: it discloses that '호출마다 토큰 1소진' (each call consumes one token) and lays out idempotency semantics (reuse only to recover a lost response, new key for a new execution). The one blemish is the sentence about keeping a 'provider-specific idempotency_key unchanged' — no such field exists in this tool's schema, so it reads as boilerplate copied from tools that do have one.

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?

Purpose is correctly front-loaded, but the middle is a four-sentence idempotency block that partially does not apply to this tool (the provider-specific key reference), and the most actionable operational fact — one token burned per call — is buried at the very end in Korean while the rest is English.

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?

With no output schema, the description carries the burden of explaining what 'status' returns (authenticated vs. expired, remaining validity, etc.) and does not do so — an agent cannot tell what it will get back or how to branch on it. The call-cost and idempotency notes are genuinely useful but do not fill that gap.

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 earns above that by explaining the request_idempotency_key's lifecycle (generate before the first request, reuse only for lost-response recovery, fresh key otherwise, unavailable to anonymous calls). It adds nothing about account_link_id, but the schema already documents it fully with auto-resolution behavior.

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 sentence 'Check NHIS EDI session status' names a specific verb and resource, and the scope is naturally separable from the sibling nhis_edi__session__login. An agent can tell this is a read-oriented status probe rather than an authentication action without opening the 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?

The description never says when to call this versus nhis_edi__session__login, nor what a status result implies (e.g., whether a re-login is needed). The guidance it does give is entirely about the idempotency key, which implies usage but leaves the tool-selection decision to inference.

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