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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds beyond that: it names the returned key (danji_id) despite there being no output schema, and positions the call as a prerequisite step in a workflow. It does not say whether multiple candidates may come back for an ambiguous name.

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?

Three short sentences, front-loaded with the purpose and ending with the actionable sequencing directive. The Korean half is a near-verbatim translation of the English half, which is mild duplication for an agent reader but still compact overall.

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 one-parameter, read-only resolver with rich annotations and no output schema, the description supplies the essential missing piece (the returned danji_id) and the workflow role. The only gap an agent might hit is handling ambiguous or zero-result queries, which the description leaves unaddressed.

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 100% and the single parameter's description already gives examples ('메이플자이, 반포동 래미안'), so the schema does the heavy lifting. The description's 'by name or neighborhood' merely restates that distinction rather than adding format or matching semantics, which is the expected baseline-3 case.

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 ('Find Korean apartment complexes by name or neighborhood') and the concrete return value ('get their danji_id'), which no sibling tool claims. The Korean sentence repeats and confirms the same scope, so an agent can distinguish this lookup tool from get_apartment_overview and the other ID-consuming siblings at a glance.

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 closing line '다른 도구를 쓰기 전에 먼저 부르세요' ('call this before using other tools') gives an explicit sequencing rule, which is exactly the guidance an agent needs for a gateway/resolver tool. It stops short of naming a when-not case or explaining what to do when the query is ambiguous, so it is clear context without full exclusion rules.

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