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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds genuinely non-schema behavior: the return baseline (close price immediately before the disclosure date), the excess-return framing versus the index, the three horizons, and the aggregate statistics reported (mean, median, share positive, 95% interval). It does not say how observations are pooled when no stock is given or how limit interacts with the statistics, which keeps this 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?

The definition is front-loaded with the resource and method, then closes with example intents, and every clause carries information. The middle sentence is dense — metric list, horizons and per-stock mode are packed into one long construction — so it is efficient but slightly harder to parse than it needs to 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?

There is no output schema, so the description carries the burden of describing return values, and it does so by naming the statistics and horizons returned. For a six-parameter, zero-required analytics tool with read-only annotations, the remaining gaps (how limit is applied, what happens when stock and market conflict) are minor rather than blocking.

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 67%, and the description compensates by exemplifying the category dimension (공급계약, CB, 유상증자, 잠정실적, 최대주주변경) and by explaining that contracts are further bucketed by size relative to revenue, which gives meaning to min_amount and to the '공급계약은 매출 대비 크기별' grouping that the schema alone does not convey. The stock parameter's dual code/name behavior and the default of 'all categories' when cats is omitted are left to the schema.

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 computation over a specific resource: post-disclosure excess returns versus the index at D, D+5, D+20, broken down by disclosure category, with an optional per-stock mode. It is clearly distinguishable from sibling listing tools such as disclosures and search_filings, which return filings rather than measured reactions.

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?

Concrete example questions ('수주 공시 나면 주가 오르나', 'CB 발행 뒤 주가', '이 회사 공시 반응') make the intended query shape unambiguous, and the note that passing stock yields per-company reactions clarifies the two modes. It stops short of explicit exclusions, so an agent is not told, for example, to use disclosures when it wants the filings themselves rather than the reaction statistics.

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