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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered structurally. The description adds genuinely non-structural context: this tool is the authoritative confirmation path and its result must not be inferred from consultation status or user claims. It stops short of describing pending/failed/unknown-verification_id behavior, which would be the remaining behavioral gap.

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?

Three short sentences, front-loaded with the action, then provenance, then the verification trigger and the anti-assumption rule. The English opener and the Korean restatement overlap slightly, costing a bit of density, but there is no 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?

There is no output schema, yet the description never says what the tool returns — whether it is a boolean, a status enum, or a pending state — which is precisely what an agent needs to act on the answer. Combined with the undocumented invalid-id case, the definition is adequate but leaves a real gap for a tool whose entire value is its return value.

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 0% — verification_id has only a type and regex pattern — so the description carries the burden, and it does: it tells the agent the value must come from begin_contact_change's return. That provenance is the single most important semantic fact and is not in the schema. It does not explain what an expired or unknown id yields, keeping it below 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 ('Read whether the specified contact change was actually applied') and ties itself explicitly to begin_contact_change as the producer of the required identifier, which cleanly separates it from the many begin_/prepare_/get_consultation_* siblings. An agent can tell it apart from begin_contact_change and get_consultation_change_status 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?

Gives a concrete trigger ('이용자가 인증·적용을 마쳤다고 하면 이 도구로 확인합니다') and an explicit negative rule ('상담의 contact_status나 이용자의 완료 발언만으로 변경 성공을 추정하지 마세요'), naming the alternative signals that must NOT be used instead. This is exactly the when-to-use / when-not-to-use / alternative framing.

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