housing_finance_calculate

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structured data. The description adds one genuinely useful behavioral rule beyond that: unconfirmed costs and inflows must not be treated as a confirmed 0 won, which signals how the calculation handles unknowns. It says nothing about the return shape, ordering, or how pagination limits affect results, which leaves a meaningful gap for a computation tool.

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 description packs a lot of value into four short sentences: what is calculated comes first, the scope boundary second, the use case third, and the data-integrity caveat last. No sentence is filler. It loses one point only because the caveat about unknowns reads as a directive that might sit more naturally alongside the parameter discussion.

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?

This is a complex tool: it has a deeply nested plan object with costs, loans, funding, payments, and debt repayments arrays, it has 25% schema description coverage, and it has no output schema. The description covers the domain and the non-persistence guarantee well, but it never describes what the returned shortfall schedule looks like or how scheduleLimit and scheduleOffset shape that response. It is adequate, but it is not complete for a tool of this complexity.

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 only 25%, so the description has to compensate for several parameters whose meaning does not come from the schema. It helps by explaining that unknown costs and inflows are not to be treated as 0 won, which conveys the meaning of the certainty/unknown pattern. However, it gives no guidance on asOf, scheduleLimit, or scheduleOffset, so an agent cannot tell from the description how the schedule paging parameters behave or what the asOf cutoff does relative to cashAsOfDate.

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 opens with a precise verb-and-resource pairing: it calculates date-by-date cash shortfalls covering contract deposits, interim payments, a balance payment, incidental costs, funding inflows, and repayment of existing loans. It also draws a boundary ('월별 신규 대출 상환은 별도 표입니다'), which tells an agent that the amortization schedule of new loans belongs elsewhere. It stops short of naming the sibling tool that owns that schedule, so the differentiation is implicit rather than explicit.

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 sentence '계산만 하며 저장하지 않으므로 여러 가정을 비교할 때 사용하세요' clearly states the use case: read-only scenario comparison where nothing is persisted. This effectively routes the agent away from housing_finance_save for what-if analysis. It does not explicitly say when to prefer housing_finance_save or housing_affordability_calculate instead, so the exclusion list is incomplete.

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