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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description adds useful behavioral context about the output: it labels stale values as STALE and returns the corrected value and filing. However, it says nothing about the scope of the correction lookup, latency, or how withdrawals differ from corrections in the response.

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?

It is a single dense sentence with the scope ('For a Korean listed company') front-loaded, and no filler. The nested parenthetical and question framing make it slightly harder to parse than necessary.

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 five-parameter tool with no output schema and only partial schema coverage, the description should clarify which inputs are required and what the result looks like. It hints at STALE labeling but leaves parameter usage and return shape largely unexplained.

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 only 40% across five parameters, and the description does not name or explain any of them. It is unclear from the text whether the tool takes a company (corp/corp_code), a report text, a date (since), or specific filing numbers (rcept_nos), so the description fails to compensate for the coverage gap.

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The description states a specific analytical task: identifying cited DART filings that were later corrected or withdrawn, and flagging values that equal a corrected value as STALE. That distinguishes it from siblings like dart_events (event listing) and kr_figure_check (figure verification), though the question-style phrasing is convoluted.

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?

There is no guidance on when to use this tool versus dart_events, kr_figure_check, or backtest_reconcile, and no indication of prerequisites such as needing a corp identifier or an existing report. Usage must be inferred entirely from the one-line purpose.

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