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

Beyond the annotations it discloses real behavior: one token consumed per call, an XBOSS job created and the result persisted, and the explicit warning that despite being a lookup this call is not purely read-only — which usefully explains the readOnlyHint=false annotation instead of contradicting it. It also gives artifact lifetimes (download_url valid 15 minutes, files kept 7 days) and recovery paths. The gap is that it never says what happens on zero matches or how pagination interacts with the job.

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 purpose and result-shape sentences are well front-loaded, but roughly half the text is generic cross-cutting boilerplate about recovery_receipt handling, anonymous lanes, sign-in behavior, and provider-specific idempotency keys that adds little for a public-data lookup. Paragraph-length platform policy interleaved with the tool description dilutes the tool-specific signal.

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?

With no output schema, the description does the work of describing the return shape (buildings with named fields, address candidates, primary) as well as side effects, cost, artifacts, and idempotency, which is substantial for a 6-parameter tool. It falls short only on pagination semantics and empty-result behavior.

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 coverage is 100%, so the baseline is 3, but the description adds semantics the schema defers to it — notably the request_idempotency_key reuse rule (same key only to recover a lost response, new key for a new execution, unavailable to anonymous calls) and the fact that output_formats produces xlsx artifacts rather than data. It adds little for pageNo/numOfRows and largely restates the bizno behavior already in the schema.

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 first sentence names a specific resource and verb: 조회 of 건축물대장 표제부 (data.go.kr 15134735) by address, and it enumerates the returned fields (건물명, 주용도, 구조, 연면적, 층수, 사용승인일, 승강기 수, 내진설계) plus the three output buckets buildings/address/primary. Nothing else in the sibling list does building-ledger lookup, so an agent can identify it immediately.

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 states the two input modes — address alone, or bizno alone to resolve a registered business location first — and says it needs no separate integration, which is actionable context. However, it never says when to prefer this over a related lookup such as opendata__nts__status or when the tool is inappropriate (e.g., no matching 지번), so usage remains implied rather than explicit.

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