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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds real behavioral context beyond them: empty results mean the graph simply lacks that ordering, and the agent must not fabricate an order. It also discloses that depth is clamped to 1–4 regardless of input and that limit is the combined step cap across all hops. The closing '읽기 전용 · 외부 호출 없음' merely restates the annotations, which keeps this from a 5.

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-loaded with the bolded purpose, then the alternative-routing list, then a ★-marked parameter block — a deliberate, scannable structure. It is dense but every section earns space; only the redundant read-only/no-external-calls restatement at the end is 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?

An output schema exists, so return format need not be explained. Across the description and schema the agent gets purpose, routing conditions, all five parameters' semantics, clamping/default behavior, and the empty-result caveat — everything needed to invoke this traversal 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 coverage is 100%, so 3 is the baseline, but the description goes further by defining each relation value's meaning (requires = prerequisite, enables = follow-up, causes = causal, contrasts = contrast; omit = all) and by disambiguating direction with a worked example — 'what comes before X' is direction=in, not out. That resolves a genuine ambiguity in the schema's bare 'in(역방향)'.

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?

Opens with a bolded, specific verb+resource: following construction sequence and precedence relations ('what must come before what'), with concrete example questions. It also explicitly states what it is not, naming path_between, scenario, compare, and k_snippets with their selecting conditions, so an agent can distinguish it from all relevant siblings without reading 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?

Gives explicit when-to-use phrasing ('기초부터 골조까지 순서', '거푸집 해체 전에 확인할 것') plus a routing list of four alternatives each paired with the condition that selects them (two endpoints → path_between, whole workflow → scenario, difference → compare, plain text/law → k_snippets). Nothing 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.