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

Annotations already establish a safe, read-only, idempotent, closed-world query, so the bar is lower, and the description still adds real behavior: it discloses the result fields (coupon %), cycle, coupon_10k per KRW 10k face, next coupon date, last trade price/yield, and 20-day trade count, plus the important caveat that yields for thinly traded names can be extreme outliers. It omits defaults for sort/limit, which keeps it from 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?

Two densely packed sentences: the first front-loads scope and filter axes, the second enumerates return fields and ends with the outlier caveat. Nothing is redundant, though the long comma-separated field list is harder to scan than a short structured block would be.

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 17 optional parameters and no output schema, the description carries the burden well by describing the returned metrics and the data-quality caveat. Gaps remain around default sort order, result cap behavior (limit max 300), and the meaning of the truncation/rank ordering, but an agent can call it correctly from what is given.

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 47%, so the description must compensate, and it does map many of the 17 parameters onto the listed filter axes (issuer/query, stock, yield, coupon, years, grade, rank, pay month, liquidity, kind, no_option). It still leaves sort, ascending, and limit undocumented in prose, and does not clarify set semantics like whether min_grade is inclusive-level or band.

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?

"장내 회사채·금융채 찾기 (KRX 상장, 만기 전)" gives a concrete verb (찾기) plus the resource, venue (KRX listed) and universe bound (pre-maturity), so an agent knows this is a screening tool over listed bonds. It does not explicitly contrast itself with the sibling `bond` (single-bond detail) or `bond_calendar`, so it stops short of a 5.

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?

Usage is implied through the enumerated filter dimensions (issuer, yield, coupon, remaining term, grade, subordination, pay month, liquidity), which tells the agent what this tool is good for. There is no explicit statement of when to prefer it over `bond` or `bond_calendar`, and no note that all filters are optional / results are a ranked screen.

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