housing_loan_calculate

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

The annotations declare that this is a read-only, idempotent, closed-world operation, so the safety profile is already covered. The description adds behavior beyond that: nothing is persisted, the monthly table shows only part of the schedule while totals cover the full term, and real-world bank approval, variable rates, and fees are out of scope. Those are genuine caveats that annotations cannot convey.

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?

Three short sentences, front-loaded with the core purpose and then the pagination caveat and the disclaimer. Every sentence adds information, and none is redundant. It is dense and terse, but not padding.

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?

There is no output schema, so explaining the return shape matters, and the description does explain that the schedule table is windowed while totals are full-term. That covers the main ambiguity for a projection calculator. A minor gap remains: the currency or units of returned totals and the date-alignment behavior are not stated.

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 0%, so the description has to carry the explanatory burden. It does define scheduleOffset/scheduleLimit semantics well: the monthly table is a partial window, while totals cover the full period. However, it says nothing about the nested loan fields (principalWon units, annualRatePct convention, termMonths, graceMonths), beyond what the labels themselves suggest.

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 uses a specific verb-and-resource pair: calculate repayment schedules (원리금균등/원금균등/만기일시상환) for an input fixed-rate loan. It also implies it is a pure calculator ('저장하지 않습니다' — does not save), which helps distinguish it from housing_finance_save/housing_profile_save, although it never names a sibling tool.

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 scope limits that it only handles fixed-rate loans and does not save hint at when to use it, and the closing caveat says variable rates and bank approval require separate confirmation. However, it gives no explicit routing to alternatives such as housing_finance_calculate, housing_payoff_calculate, or housing_affordability_calculate, so the agent must infer the choice.

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