get_cafeteria_menu_stats

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds critical nuance: '메뉴 건수' is line count not dish count, clarifying what the numbers represent. It also states the geographic scope. While it does not mention output format or pagination, an output schema exists, and the read-only nature is implied by '조회' (inquiry). The key behavioral nuance is effectively disclosed.

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 description is laid out in a clear, front-loaded structure: a one-line summary, followed by scope, a crucial note, and parameter guidance. It is somewhat verbose but each sentence earns its place—the note about line counts vs dish counts is essential to prevent misinterpretation. The parameter explanation is directly actionable.

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?

Given the tool is a simple stats query with one optional filter parameter, the description covers the essential aspects: what is returned (counts by meal and location), the semantic nuance, the filter behavior, and the coverage. It does not explicitly state that an empty location returns all locations, but that is reasonably implied. Since an output schema exists, return structure is handled separately. The description is sufficiently complete for an agent to invoke the tool correctly.

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%, so the description must fully explain the parameter. It does: location is described as a partial-match filter on cafeteria region name with concrete examples ('서울역', '부산', '대전', '본사'). This goes well beyond the schema, which only specifies a string type and default. The agent can correctly construct filter values based on this guidance.

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 uses a specific verb ('조회' = inquiry) and names the resource (구내식당 메뉴 건수 - cafeteria menu counts). It clearly distinguishes the metric: menu line counts per meal (조식·중식·석식), not actual dish variety, and specifies the nationwide scope with example locations. No sibling tool appears related, so differentiation is inherently clear.

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's purpose and provides usage context via the location filter examples ('서울역', '부산'). It does not explicitly mention when not to use it or alternative tools, but given the unique nature of the tool among siblings (no other cafeteria-related tool exists), the context is sufficient. The filter semantics are clearly described, making it easy for an agent to decide when to call this tool.

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