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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond that with the secrets policy ("Secrets are never accepted as MCP inputs"), the retry/idempotency contract (replay with the same key recovers the request, otherwise a second call is a brand-new request), and the per-call credit cost ("호출마다 토큰 1소진"). The one meaningful omission is what the resulting session looks like and how long it stays valid, which matters since there is no output schema.

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 this FIRST," is the first clause, so the definition is properly front-loaded. The idempotency material runs long relative to a single optional parameter and the Korean cost note is tacked on at the end, but no sentence is outright redundant.

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 0-required-parameter session bootstrap with annotations present and no output schema, the description covers ordering, credential handling, idempotent replay, and cost. It stops short of describing session lifetime or what happens when the account link cannot be resolved, which are the remaining things an agent would want to know before calling.

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 schema already documents both parameters and a baseline of 3 would be acceptable. The description earns credit above baseline by explaining the lifecycle of `request_idempotency_key` — generate before the first request, persist it, reuse only for same-argument recovery — and by warning that a provider-specific `idempotency_key` is a separate field that must not be conflated.

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?

States a specific verb and resource: "Create a KB Kookmin Bank fast-account inquiry session from an existing account link," which matches the tool name rather than restating it. The provider scoping ("for this provider") separates it from the many other `session__login` siblings such as hana_fast_account__session__login or ibk_fast_account__session__login.

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" is an explicit ordering rule that tells the agent when to invoke it. The idempotency paragraph likewise spells out when to reuse the key (recovering a lost response with identical arguments) versus when to mint a new one (a new execution). What's missing is any when-not condition or named alternative if a session already exists.

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