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

Annotations already declare readOnlyHint=true, so the bar is lower, yet the description adds real context beyond them: no authentication needed, the per-call token cost ('호출마다 토큰 1소진'), and the idempotency-key lifecycle. The stray note about a 'provider-specific idempotency_key' field that does not exist in this schema adds mild noise rather than 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?

Purpose is nicely front-loaded, but the description spends four sentences on one optional parameter, with 'Without it, calling again remains a new request' largely restating the preceding sentence and an irrelevant note about a provider-specific idempotency_key field. Trimming those would sharpen it.

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 single-optional-parameter read tool with annotations and no output schema, the description covers auth posture, cost, return fields, and key handling. Only the empty-result case and ordering relative to quick_summary__get are 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 nominally 100%, but the schema's own description is circular ('see the tool description'), so the description genuinely carries the semantics: when to generate the key, when to reuse it, and when it is unavailable. It does not explain the pattern/length constraints, and the phrase 'not available to anonymous taste calls' is confusing.

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 (list IBK account links registered by this caller) and even names the output identifiers and the downstream consumer ('the balance summary tool'), which lets an agent distinguish it from quick_summary__get without opening a schema. The no-login-required lead sentence further separates it from the session/login siblings.

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?

Explicitly establishes the no-credential precondition and gives clear when/when-not rules for the idempotency key (generate before the first authenticated request; reuse only to recover after a lost response; new key for a new execution). It stops short of stating sequencing relative to the balance-summary tool or how to behave when zero accounts are registered.

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