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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description does add real context beyond them: the tax basis is 고시 공시가격 and the calculation mirrors the Richgo tax calculator, signalling this is a modeled estimate rather than an official assessment. It stops short of noting exclusions, rounding, or that the figure depends on the current year's rates.

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?

Two sentences, front-loaded with the core purpose and the tax components, then the assumptions. The English and Korean sentences are largely duplicative, which costs a little, but the bilingual phrasing is defensible for a Korea-specific real-estate tool and nothing is padded.

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?

Given a read-only, closed-world, two-parameter compute tool with fully described inputs and no output schema, the definition tells the agent enough to invoke it correctly and interpret the result as an estimate. The only real omission is the scope of the calculation (what taxes/fees are excluded and that results are indicative).

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 both parameters (pyeong, danji_id) are already documented in the schema, including the fallback '비우면 대표 평형'. The description adds only marginal semantics — that the result is keyed to the given size and driven by the complex's published price — which is the expected baseline-3 outcome when 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?

States a specific computation: this year's holding tax (property tax + comprehensive real estate tax) for one home of a given size, under a single-home owner-occupier assumption, based on the official published price. That is far more specific than the title alone and is distinguishable from all the sibling listing/market tools, though it never names a sibling to contrast with.

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 assumptions embedded in the text ('single-home owner-occupier', 'based on the official published price') implicitly define the conditions where the result is valid, which is genuinely useful routing information. But there is no explicit statement of when to use this versus e.g. get_apartment_overview, nor what happens with multi-home or non-owner-occupied cases.

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