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

Annotations declare readOnlyHint=false and destructiveHint=false, yet the description explains the surprise: "요청 처리 시 XBOSS 작업을 생성하고 처리 결과를 저장합니다... 순수 읽기 전용이 아닙니다" — this call creates a job and stores a result. This is exactly the context an agent cannot infer from annotations alone. It also discloses the login prerequisite, per-call and per-account token costs, the 15-minute download_url lifetime, the 7-day file retention, the idempotency-key recovery contract, and the anonymous recovery_receipt obligation — all behavior that the structured fields do not carry.

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 definition is a dense block mixing prerequisites, artifact retention, anonymous recovery receipts, idempotency policy, token accounting, and a disclaimer, in alternating English and Korean. Much of it is boilerplate that is irrelevant to a transaction search, such as the anonymous receipt and sign-up warnings, and does not help an agent decide or parameterize the call. The leading element is a prerequisite, not the purpose, so the structure is also not front-loaded on what the tool does.

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 9-parameter read tool with a fully documented schema and no output schema, this definition covers login preconditioning, idempotency, artifact return behavior, file retention, and job-creation side effects. The remaining gaps concern the shape of the returned page — pagination or row limits, and the fields expected in artifacts[] — but nothing essential to invoking the tool correctly is missing.

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 schema description coverage is 100%, so the schema already documents date formats, sort order, output_formats, and the three-way account selector. The description does not add syntax or format detail beyond the schema; the only echo is the exclusive-choice rule for the account parameters. This is in line with the baseline where the schema does the heavy lifting.

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 second sentence states a specific verb and resource: "Search one evidence-backed Woori Bank transaction-history page through an existing provider session." It is clearly distinguishable from the sibling woori_bank__accounts__list. However, the front-loaded sentence is a prerequisite statement, and phrases like "evidence-backed" and "one page" are unexplained, so the core purpose is not stated first and is not stated crisply.

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 definition gives an explicit precondition ("REQUIRES prior woori_bank__session__login call with same account_link_id") and a recovery path ("If a link has expired, call xdata__job__result with the job_id"). It also gives an account-selection rule: send exactly one of the three account parameters. It lacks an explicit statement of when not to use this tool, but the login gate and account-selection rule cover the main branching decisions an agent needs.

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