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

Annotations already mark this as non-read-only, non-idempotent and closed-world; the description adds the complementary behavioral facts: the key is a secret to be stored safely, it is placed in the Authorization header of this server's connection config, it is retrievable only once, and it is not to be transmitted anywhere except trading.pe.kr. That is genuine value beyond the annotation set. It does not address failure modes (already claimed, unapproved application, invalid token), which keeps it below a 5.

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?

Four short sentences, front-loaded with the operative action and immediately followed by the secret-handling obligations, so nothing important is buried. The trailing parenthetical English restatement is a small redundancy but aids readability.

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 two-required-parameter tool with no output schema and non-idempotent semantics, the description covers purpose, prerequisite, one-time nature, and secure storage/transport guidance — enough for an agent to call it correctly. The main remaining gap is error behavior when the claim is rejected or already consumed.

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 description coverage is 100% and both parameters already carry descriptions ('application_id' tied to the apply_for_key response, 'claim_token' as the tpc_… receipt token). The description reinforces the pairing with an approved application but adds no format or validation detail beyond the schema, so the baseline of 3 applies.

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 names a specific verb and resource ('승인된 신청의 API 키(tpk_…)를 한 번만 받는다') and even gives the key's prefix format, which is concrete. It implicitly separates itself from apply_for_key by requiring an already-approved application, but it never names a sibling tool explicitly, so differentiation is inferred rather than stated.

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?

'승인된 신청' and '한 번만' establish the precondition (approval granted) and the calling constraint (retrieve exactly once), which is clear usage context. What is missing is explicit routing — e.g. use check_application first if unsure of approval status, or apply_for_key if no application exists — so the agent must infer the alternative path.

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