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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description discloses real side effects: one token consumed per call, an XBOSS job created and its result stored, and an explicit statement that the call 'is not purely read-only' despite reading institution data. That is substantive context the annotations cannot convey. It loses a point for the boilerplate closing line about provider data changes, which is generic, and for burying these traits in dense mixed Korean/English prose.

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 critical instruction is correctly front-loaded, but the middle section is repetitive ('Without it, calling again remains a new request') and mixes a long English idempotency paragraph with untranslated Korean clauses. Sentences such as 'it is a different field' and the closing data-change boilerplate do not clearly earn their place.

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-creating tool with side effects, cost, and no output schema, the description covers sequencing, idempotency, token cost, and the non-read-only nature — the things an agent most needs before calling. It does not describe what a successful login returns (session handle, expiry, behavior when already authenticated), which is a gap given there is no output schema.

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 adding operational meaning to request_idempotency_key — when to generate it, when reuse is legitimate, and that reuse with different arguments is wrong. account_link_id is left entirely to the schema, and the phrase 'not available to anonymous taste calls' is opaque enough to confuse rather than clarify.

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 description states a concrete verb and resource: 'Create a Shinhan easy-inquiry session from a registered ID/password account link.' The provider qualifier ('for this provider') and the id/password account-link source distinguish it from the NPKI-style login siblings. It stops short of naming any alternative login path, so differentiation rests on the provider name alone.

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?

Ordering guidance is explicit and front-loaded: 'Call this FIRST before any other tool for this provider.' The idempotency paragraph also gives clear use rules — generate before the first request, reuse only to recover a lost response, new key for a new execution. No when-not-to-use case or alternative is described, which keeps it off a 5.

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