get_leased_assets

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

With no annotations provided, the description carries the full burden. It clearly indicates a read-only query ('현황 조회') and enumerates the data returned, implying no side effects. It also notes the data volume (1,773 records) and partial-match filter behavior, providing useful behavioral context beyond mere operation. However, it doesn't explicitly mention pagination or any limits, but for a simple read-only lookup, this is acceptable.

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 well-structured: it opens with the core purpose, lists the data fields, clarifies the distinction from a sibling, and then details each parameter with examples. Each sentence contributes value without redundancy. It is longer than two sentences but remains efficient and front-loaded with the primary directive.

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?

The tool is relatively simple with two optional parameters, and the description covers the data returned, parameter semantics, and a key sibling distinction. An output schema exists, which likely documents the return structure, so nothing critical is missing. The description is sufficient for an agent to invoke the tool correctly without additional context.

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 has 0% description coverage, so the description must compensate, and it does excellently. It explains that location is a partial-match filter on asset location with examples ('서울', '대전') and facility_name is a partial-match filter on facility name with examples ('서울역', '용산역'), giving agents precise meaning and usage patterns beyond just the schema's string type and default.

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 explicitly states the tool queries leased assets of the Korean Railroad Corporation and lists the exact fields provided (location, facility name, contract period, area, annual rent), making the purpose unambiguous. It also directly distinguishes itself from the sibling tool get_lease_stores by clarifying this is an asset/financial perspective rather than store operations, which helps an agent select correctly.

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 names the sibling get_lease_stores and draws a clear distinction, effectively telling the agent when not to use this tool (when store operational info is needed) and when to use it (for asset/financial data). It also provides filter usage examples (e.g., '서울', '대전') that clarify how to apply parameters, though it does not explicitly state broader scenario conditions.

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