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

Annotations already cover safety (readOnly, idempotent, non-destructive), but the description adds substantial behavioral context an agent could not infer: photos survive only in a snapshot since court sources delete them, fail_count can legitimately disagree with the schedule rows, tracking/price_events may be empty and empty ≠ no change, and current_min_bid_10k may be stale when min_bid_source='item_list'. This is exactly the value-beyond-annotations case.

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?

Front-loaded and each paragraph addresses a real failure mode, but it is long and dense with parenthetical warnings and emoji emphasis that could be trimmed. It earns most of its length but is not tight; several caution clauses (kind_note, fail_count_note, min_bid_note) could be consolidated.

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?

No output schema exists, so the description must carry return-value semantics, and it does: it explains the meaning of 유찰 rows, null result rows, min_bid_10k absence with kind_note, note fields, and snapshot-emptiness caveats. It is near complete for a read-only lookup, missing only a compact restatement of the primary return shape or pagination 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 description coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema: it warns not to invent meaning for null result rows, explains that min_bid_source=item_list indicates staleness for the returned current_min_bid_10k, and clarifies what court_schedule rows represent. These are output-semantics not captured in parameter docs.

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 (경매 사건 하나의 유찰 이력·가격 변동·물건 사진 조회) and distinguishes itself from siblings like realty_get_auction_case and realty_search_auctions by naming the exact fields it owns (유찰 이력, min_bid_10k 저감, 사진 URL). An agent can tell it apart without opening the schema.

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?

Gives an explicit trigger question class ("몇 번 유찰됐어? 얼마나 떨어진 거야? 사진 있어?") which tells the agent when to call this. However, it never names the alternative tool (e.g. realty_get_auction_case) or an exclusion case, so routing is clear only by field ownership, not by explicit contrast.

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