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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered by structured data. The description still adds real behavior beyond that: an exact provider-side rejection ('6개월이상은 조회할 수 없습니다.') and the workaround of splitting ranges, an auth prerequisite, and a per-call token cost ('호출마다 토큰 1소진'). It does not cover pagination behavior or result shape, but the disclosures it does make are specific and non-obvious.

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?

Purpose, prerequisite, and the six-month limit are well front-loaded. But five sentences of idempotency-key mechanics follow for an optional field on a read-only search, which is disproportionate to the operation and crowds out anything about results or pagination. Tightening that paragraph would strengthen the definition.

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 read-only paginated list with no output schema, the description covers the critical unknowns: authentication precondition, maximum query window and the error you get when exceeding it, direction encoding, and per-call cost. The remaining gaps are pagination semantics (page_num/page_size defaults are only in the schema) and sibling selection guidance.

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 the schema already documents date formats, the prh_sls_cl_cd enum and defaults, and the account_link_id resolution rules. The description repeats the date format and the '01'=issued/'02'=received mapping rather than adding to them. Baseline 3 is appropriate; it does clarify that the idempotency key is a separate field from provider-specific keys, which is a small genuine addition.

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: 'Search e-tax invoices by date range.' An agent knows exactly what it retrieves. However, it never distinguishes this list call from the closely named siblings hometax__etax__invoice__search_detail, search_summary and search_statistics, so the agent must guess which of the four to use for a given need.

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 concrete when-to-use conditions: a prior hometax__session__login with the same account_link_id, a date range under six months, and how to split longer windows into several calls. It also explains when to reuse vs. regenerate the optional idempotency key. What is missing is any routing advice between this tool and the detail/summary/statistics siblings.

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