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

Annotations already cover read-only/idempotent/closed-world, yet the description adds material behavior the agent cannot get elsewhere: abstained=true means the den genuinely lacks a definition and must not be paraphrased, exact=false flags an inexact name match, and the tool never returns normative values. It also restates the read-only/no-external-call profile without contradicting 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?

Information is front-loaded: purpose first, then alternatives, then parameter notes, then output-flag semantics. The arrow-and-star shorthand is dense and effective, though the block is long enough that a reader must scan several segments to find the two output flags.

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 three-parameter lookup with an output schema plus full annotations, nothing an agent needs is missing: when to call, when to use a sibling, how to form each argument, and how to interpret abstained/exact in the response.

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 100%, but the description still adds meaning: term must be a single term rather than a question sentence or a list of terms, limit is a disambiguation cap truncated to 1~5 with default 3. as_of's YYYY-MM-DD format merely repeats the schema, so this stops short of a 5.

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·건설 용어 하나의 뜻을 돌려준다') and anchors it with concrete example questions. It also explicitly carves out scope ('이 도구는 정의 한 덩어리만 준다 — 기준값은 주지 않는다'), making it distinguishable from every sibling.

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 an explicit trigger condition ('X가 무엇인가' 질문) and then routes to the right alternative for each adjacent need: k_snippets for numbers/articles, enumerate for taxonomies, answer_why for causation, compare for contrasts, path_between for relations. This is about as complete as routing guidance gets.

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