site_menu

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

No annotations exist, so the description carries the full disclosure burden. It does disclose the important behavioral trait that the output is a menu code intended for site_page, but says nothing about read-only nature, what an empty keyword returns, or result size/pagination.

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 sentences: the purpose with a compact example set, then the follow-up workflow. Zero filler and the core identification is front-loaded.

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?

An output schema exists, so return-format explanation is unnecessary and the description correctly focuses on the workflow handoff to site_page. The only gap is the semantics of an empty or broad search, which an agent might need in practice.

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 description coverage is 0% for the single 'keyword' parameter, so the description must compensate. The example keywords do convey the expected value domain, but the empty-string default (which presumably lists everything) is never explained.

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 and resource: searching the Ulsan University homepage menu/sitemap. Explicitly separates itself from site_page by describing the follow-up handoff ('나온 mCode를 site_page에 넘기면'), so an agent can tell the two apart from the description alone.

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 keyword examples ('장학', '기숙사', '셔틀', '등록금'…) show concretely what kind of queries belong here, and the second sentence defines the downstream step with site_page. It does not, however, contrast itself with the sibling site_search, leaving that distinction to inference.

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