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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description goes substantially beyond that by explaining why the call is not purely read-only (token consumption per call, XBOSS job creation and result storage), and by disclosing the upstream NTS 3-month validation with its exact error text. It also explains the response count semantics (totalCount equals pageInfoVO.totalCount, collectionMeta.complete vs collectedCount), which is behavior an agent cannot get from the annotations.

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 prerequisite is front-loaded in capitals and the date-range, count and idempotency rules follow in a logical order, so an agent can extract the operational constraints quickly. It is dense but mostly earns its length; the trailing Korean boilerplate about 기관 데이터 변경 and the stray note about 'anonymous taste calls' are low-value filler that could be trimmed.

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 10-parameter query tool with no output schema, the description supplies what the schema cannot: auth prerequisite, range limit and chunking, pagination termination logic, and an explicit account of the returned count fields. Only the relationship to the sibling sales-history tool and any per-call rate expectations remain unstated.

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 real meaning beyond the schema for from_date/to_date (the 3-month ceiling and the required splitting strategy) and for request_idempotency_key (generate before first request, reuse only to recover a lost response, new key for a new execution). It also clarifies implicitly how fetch_all_pages/max_pages interact with collectionMeta.

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 states a specific verb and resource ('Search cash receipt purchase history') and the Korean title identifies it as 현금영수증 매입 내역 조회. It does not name the closest siblings (hometax__cash_receipt__sales__search_history or daily_issue__search), so an agent must infer the purchase-vs-sales distinction from the tool name alone.

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?

Strong operational guidance: it declares the session-login prerequisite with matching account_link_id, mandates from_date/to_date, explains that ranges over 3 months are rejected and must be split into chained calls, and tells the agent when to request the next page versus when collectionMeta.complete means it is done. It also gives clear when-to-reuse versus when-to-rotate rules for the idempotency key. The only gap is that no alternative sibling tool is named.

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