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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description usefully reveals that verification is against official sources (BOK base rate, KTB yields, DART filings) and distinguishes consolidated vs separate statements, but says nothing about tolerances, how mismatches are reported, or coverage limits.

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?

A single front-loaded sentence: verb+resource first, then a compact enumeration of the specific checks. Dense but every clause carries domain information; only mild criticism is that the enumeration could be slightly better structured as a list.

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?

No output schema exists, and the description never says what the check returns – a pass/fail verdict, a list of discrepancies, corrected values – which is central for a validation tool. The input side is reasonably covered, but the missing output behavior leaves a real gap.

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 only 25% (only as_of is documented). The description implicitly clarifies that corp refers to a listed company, year to a fiscal period, and the sources behind as_of, but it never explicitly maps any parameter, leaving half the semantics to inference.

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 ('check') plus the resource ('numbers in a Korean finance text') and names the authoritative sources (Bank of Korea, KTB, DART, KRW rates). The enumeration of checks (percent vs percentage point, 조/억, consolidated vs separate) makes the scope unmistakable and separates it from data-fetching siblings like kr_fx and kr_rates.

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 by the scope statement – verify figures in Korean finance prose – but there is no explicit when-to-use/when-not guidance or naming of alternative tools. An agent can infer the context but gets no routing help against siblings such as dart_events or kr_law_article.

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