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

Annotations already cover read-only/idempotent/non-destructive safety, but the description goes well beyond them: it discloses the ranking rule (관련도 → AI 준비 구간 → daily shuffle, explicitly not performance or paid ranking), defines the ai_ready field, and explains that results carry a match field showing the evidence (본사/납품 실적/시공 가능 지역). That is meaningful non-obvious behavior for a search 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?

Purpose and scope are front-loaded, and every clause (ranking rule, ai_ready meaning, region matching, category pointer) carries information an agent needs. It is a dense single paragraph without internal structure or line breaks, which slightly hurts scanability, but there is no obvious filler.

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?

With 6 optional parameters, no output schema and only 83% schema coverage, the description compensates by explaining ordering, the ai_ready and match fields, and region semantics — effectively covering the return behavior. It leaves cert, query and limit to the schema, but nothing critical for correct invocation is missing.

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 already 83%, so the baseline is 3, but the description adds real semantics: region matches against three separate sources (본사 소재지, 최근 1년 납품 실적 지역, 등록 시공 지역) with match explaining which fired, and category/group are tied to the 조달청 물품분류 vocabulary and list_categories. This exceeds what the schema alone conveys.

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 names a concrete verb+resource (finding Korean vendor cards built from procurement data) and specifies the underlying sources (종합쇼핑몰 계약 품목 + 최근 1년 조달 실적). It does not clearly distinguish this from siblings find_businesses or find_local_shops, and the bracketed prefix mentioning '입찰 공고 찾기' briefly muddies the line with find_public_bids. Still, an agent can tell this is the procurement-vendor search.

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?

Usage context is implied rather than stated: ordering rules, region-matching semantics and a pointer to list_categories for the category vocabulary are given, but there is no explicit 'use this instead of X when Y' guidance against the five siblings. The agent must infer when this tool is preferable to find_businesses or find_local_shops.

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