core.pipeline

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

Goes well beyond the annotations: hard limits (최대 50단계, 깊이 10), failure propagation semantics ('실패한 단계의 하류는 skipped'), and the resume mechanism are all disclosed, none of which readOnlyHint/idempotentHint convey. It does not, however, explain how the two timeout parameters interact or what the response contains on a partial failure, so it stops short of full behavioral coverage.

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?

Four dense sentences, each adding distinct information: purpose, step schema and limits, reference syntax, failure/resume behavior, then the sibling hand-off. The differentiating constraint and the alternative are both front-loaded with no filler.

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 nested-DAG orchestrator with a published output schema, the description covers the mechanics, limits, failure semantics, and the alternative tool, so an agent can construct a valid call. The omission of the timeout parameters' semantics is the remaining gap, but it is bounded since both have sane schema defaults.

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 0%, so the description must carry the load — and it does for the only required parameter, spelling out the {id, tool, args} shape and the ${단계id.result.필드} interpolation syntax that the schema does not express at all. step_timeout_s and pipeline_timeout_s (defaults 2/30) are never mentioned, leaving two of three parameters documented only by a bare title.

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+resource ('의존 관계(DAG)를 가진 도구 호출을 순서대로 실행') and immediately scopes it against the sibling that does the opposite ('서로 독립인 호출은 core.batch 를 쓴다'). An agent can distinguish core.pipeline from core.batch, core.add, and core.pipeline_resume without opening any schema.

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?

Gives an explicit selection rule — use this tool when steps depend on each other, use core.batch when they are independent — and names the recovery path (pipeline_id 로 재개) that pairs with core.pipeline_resume. Both the when and the when-not are stated rather than inferred.

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