get_bill_history

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

With no annotations provided, the description carries the behavioral burden. It reveals useful behavioral traits: it consolidates multiple major events including meetings, and it orders them by date (날짜순). It also implies a read-only operation without saying so. However, it does not disclose output size limits, pagination, or whether the returned data is limited to major events only, which could matter for an agent deciding whether this tool satisfies a query.

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 Korean description is compact: two sentences of behavior and then a concise Args section. The main behavior is front-loaded in the first sentence, and the parameter explanation is short. No filler or repetition. It loses one point because the Args line is somewhat redundant with the schema (bill_id appears both places), but it earns its place by adding the format alternatives. Overall, every sentence contributes.

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 an output schema present and the tool has a single parameter, so the description need not explain return values in detail. It explains what it returns (all major history including meetings, ordered by date), which is the key behavior an agent needs. Gaps are minor: no mention of page size, date range limits, or whether 'major history' excludes certain event types. Still, for a read-oriented lookup with one parameter and an output schema, it is sufficiently complete.

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?

The input schema only declares bill_id as a string with no description, and schema coverage is 0%, so the description must compensate. The description does so by explaining bill_id can be either an 의안 ID like 'PRC_...' or a 의안 번호 like '2200001', and gives a realistic example. That is genuinely useful semantic information beyond the schema. It would be even better if it clarified how to distinguish the two formats or what happens if an invalid ID is provided, but for one parameter it is quite adequate.

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 clearly states a specific verb ('통합하여 조회합니다' — integrates and retrieves) and resource (특정 의안의 모든 주요 이력). It also specifies the exact scope: '발의부터 현재까지' and '회의 포함', which distinguishes it from sibling tools like get_bill_voting_results, get_bill_details, or bill_timeline. Even without reading schemas, an agent can infer it returns a chronological consolidated history of a bill rather than a single detail.

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?

The description explains the tool is useful for '타임라인 생성이나 연혁 분석' (timeline creation and history analysis), giving a clear usage context. It does not explicitly list when NOT to use it or name alternative sibling tools, so it misses the full when/when-not guidance. But the use-case hint is enough to route an agent appropriately among the many legislative tools.

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