Consultation output

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses real behavioral traits: it refuses to register scenarios lacking 근거, auto-injects the 세무사법 safety-line text, and forces multi-scenario output for D–F grades rather than a single number. These are enforcement behaviors an agent would not otherwise know. It omits return/pagination details, but the enforcement profile is well covered.

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 opening sentence is front-loaded and clear, but the body is a dense, bilingual block with circled numerals, parenthetical design-doc references, and compressed tier notation that takes effort to parse. Information density is high with little waste, yet readability suffers.

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 terminal formatter with no output schema and an annotations-covered safety profile, the description supplies the enforcement contract, the scenario element shape, and the call order. It still leaves the shape of the produced output and three of five inputs (extra_flags, issue_grade, dividing_issue) undocumented, so an agent lacks full guidance for non-default invocations.

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?

With 0% schema description coverage, the description must carry the parameters. It partly does: it details the scenarios element shape ({라벨, 세액, 전제, 근거}) and ties 차액=리드 스코어 tiers to the lead_threshold default (500만). But extra_flags, issue_grade, and dividing_issue are never explained, so the burden is only half met.

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 states a specific role: the standard output formatter for a consultation result and the final pipeline stage that enforces the §11 output protocol. It enumerates concrete formatting rules (no single-number results, forced side-by-side scenarios, auto safety-line text), which makes the purpose concrete. It does not, however, distinguish itself from the sibling format_consultation_report, leaving the agent to infer which formatter applies.

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 gives an explicit ordering: run tree ③→①→②→④ judgments, then calc_* computations, then format each scenario's tax amount with this formatter. That tells the agent when in the workflow to call it. It stops short of stating exclusions or naming the alternative sibling formatter for other cases.

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