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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, and the description adds useful context: results come from public licensing records rather than ratings, so there are no stars, and the regional coverage spans nationwide cities and districts, with '화성 동탄' treated as a separate '동탄'. It does not say how results are ordered (by years of operation?) or how uncertainty is reported, but it adds real value beyond the annotations.

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 three sentences follow a sensible order: what the tool does, then when to use it, then which regions are covered. The region enumeration sentence is long and reads like an internal note, but every sentence still carries information an agent needs.

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 7-parameter, zero-required search tool with no output schema, the definition covers the data source, the scope and the typical queries. It never sketches the result shape, the ordering, or what include_uncertain actually yields in the response, which the absence of an output schema makes more significant.

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 86%, so the architecture carries most of the parameter explanation. The description restates the region granularity rules (Seoul gu, Gyeonggi si/gun, metro gu/gun, and the special '동탄' case) that the region parameter already documents, so it adds little new meaning; no detail is added on how limit or min_years interact.

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 definition states a concrete verb+resource ('같은 자리에서 오래 영업 중인 음식점을 찾습니다') and pins down the data source ('공공 인허가 기록 기준, 별점 없음'), which separates it from a ratings-based restaurant search. It does not name the siblings find_restaurants_near or get_restaurant, 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?

It lays out concrete example invocations ('동탄 국밥 맛집', '오산 노포', '평택 서정동 중국집') and the situations that call for it: searching long-running/노포/old restaurants, or writing about them. There is no when-not-to-use statement (for example, when a proximity search or a single-restaurant lookup is the better fit), which is the one missing piece.

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