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

Annotations already cover read-only/idempotent/no-external-call, and the description adds substantive traits beyond them: violations are never dropped from the answer, unreviewed axes are disclosed in the result, and jurisdiction only prioritizes matching clause records rather than querying separate ordinances. That is meaningful behavioral disclosure not present in structured fields.

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?

Front-loads the purpose, then alternatives, then input guidance, then caveats. It is dense with arrows and star markers and runs long, but nearly every clause carries distinct operational information, so little is wasted.

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 six-parameter review tool with an output schema, the description covers purpose, alternatives, input semantics, interaction with site_context, and result behavior. Return values need not be explained because an output schema exists, so nothing an agent needs to invoke it correctly 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 description coverage is 100%, so the baseline is 3, but the description adds real meaning: the input is parsed structure rather than an image, rooms is the only required field, and missing adjacency/circulation specifically narrows which requirements are checked. It also specifies the jurisdiction key format and its lookup behavior, exceeding what the schema 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?

States a specific verb and resource (건축 법규 관점에서 평면도·배치도를 검토) and enumerates the exact axes checked (채광·환기·피난·면적 요건 위반). It also names the sibling it is not for (k_snippets, answer_why, emotional_palette), so an agent can distinguish it without opening any schema.

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?

Explicitly states the triggering condition (사용자가 도면을 공유하거나 공간 구성 검토를 요청) and routes to named alternatives for adjacent needs, plus a required ordering rule (site_context를 먼저 부르고 jurisdiction을 넘긴다). Nothing about when-to-use is left to inference.

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