guide

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

With no annotations supplied, the description carries the full behavioral burden: it discloses the kind of content returned (rules, ordering, spec instructions), which implicitly frames it as an information-only, non-mutating call. It never explicitly states that it is read-only, has no side effects, or is side-effect-free to call repeatedly, and it says nothing about the shape or length of the returned guide. Adequate disclosure of content, thin disclosure of behavior.

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?

Two short sentences with zero filler: the first enumerates what comes back, the second delivers the call-first instruction. The ordering is appropriate — content first, then the usage trigger — and nothing is repeated from the schema.

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 zero-parameter, no-annotation tool with no output schema, the description covers the essential questions: what it returns and when to call it. Since no output schema exists, the three named content categories are the only description of the return value, and they are enumerated but not characterized (no format, length, or whether the returned rules are mandatory). Complete enough to invoke correctly, slightly thin on what to expect back.

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 tool takes zero parameters, so per the baseline this dimension starts at 4. The description correctly implies a parameterless call — it describes the tool as simply returning content with no filtering or selection arguments, matching the empty input schema. No meaning is lost by omitting parameter discussion.

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 verb (돌려준다/returns) and enumerates the concrete payload: workflow order, exam-material quality rules, and how to write figure specs. That distinguishes it from siblings such as find_data, make_figures, or set_style, which perform work rather than explain it. It falls short of 5 only because '작업 순서' (work order) is left abstract — which workflow, for what end-to-end task, is not named.

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?

It gives an explicit routing rule: call this first on first use ('처음 쓸 때 먼저 부른다'), which is exactly the when-to-use signal an agent needs for an onboarding tool among 13 siblings. It does not state when the tool can be skipped or whether it should be re-called later in a session, so it stops short of full when/when-not coverage.

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