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

With readOnlyHint, idempotentHint and destructiveHint already declaring a safe, side-effect-free read, the description's added value is provenance ('reported contracts (MOLIT)') and the fact that a contract count accompanies the median. It does not flag the sample-size caveat that makes the contract count matter, nor any recency/coverage limits.

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 tight sentences: what it measures, what questions it fits, what it returns. Front-loaded and free of filler, with the return statement earning its place since there is no output schema.

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?

Six parameters, one required, all documented in the schema, and the description covers return shape in lieu of an output schema. Minor gap: it doesn't explain that a low contract count weakens the median, which is the main interpretive risk in using this data.

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 coverage is 100% with three enums fully described, so the schema carries parameter meaning on its own. The description adds nothing per-parameter — the rent/jeonse/sale distinction it mentions is already spelled out in the transaction enum description.

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 resource and metric (median monthly rent/deposit, jeonse deposit, apartment sale price) scoped to 'an area of South Korea', with a named data source (MOLIT reported contracts). It implicitly separates itself from housing_compare and housing_trend by describing a single-area, point-in-time median, but never names those siblings, so an agent must infer the division of labour.

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 second sentence gives concrete question shapes the tool answers ('what rent costs in a Seoul district', 'how big a jeonse deposit is', 'what apartments sell for'), which is strong affirmative guidance. It stops short of stating when to prefer housing_compare, housing_trend or housing_report instead.

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