Consultation report

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 adds real behavior beyond that: it enforces a validation rule ('출처 없는 설명은 리포트 전체 거부'), preserves a 'no-assertion' convention via format_consultation_output, and discloses that it auto-derives recommended-search queries returned as '추천검색'. These are concrete traits an agent could not infer from 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 English opening sentence is a good front-loaded summary, but the Korean block largely restates it while layering multiple parenthetical rules, inflating length without proportional new information. It is readable but not tight.

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 6-parameter, no-output-schema tool with zero schema description coverage, the description conveys the pipeline role, section layout, the source-mapping validation rule, the scenarios condition, and an extra structured return ('추천검색'). The main gaps are the two undocumented params (issue_grade, dividing_issue), but overall it is sufficient to call the tool correctly.

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 0%, so the description must carry parameter meaning; it does so for four of six: conclusion (placed at top), evidences (explanations 1:1 with sources, whole-report rejection), owner_qa (§3 answers with grounds), and scenarios (alternates when the issue splits the tax amount). The remaining issue_grade and dividing_issue are never explained, and the object shapes behind the additionalProperties arrays are undocumented. Partial compensation only.

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+resource ('Format a consultation result as a report') and enumerates the output sections (conclusion, grounds mapped to sources, tailored Q&A). It also references the sibling format_consultation_output as a reuse dependency, giving partial differentiation. It stops short of fully contrasting with that sibling's role, so it lands at 4 rather than 5.

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?

'상담의 마지막 단계' (the final step of consultation) clearly fixes when the tool is used, and it gives a conditional ('쟁점으로 세액이 갈리면 scenarios를 함께 넘겨') for passing an optional parameter. There is no explicit when-not or alternate-format selection guidance, but the context is unambiguous.

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