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

Annotations already declare readOnlyHint and openWorldHint, and the description adds valuable behavioral context: '결과는 저장하지 않고 매 호출마다 즉시 조회합니다' (Results are not stored and are queried immediately each call), plus the per-call point cost. These details go beyond the annotations and help the agent understand the tool's stateless, real-time nature, though response format is not described.

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 description is concise, beginning with the core purpose in the first sentence, followed by useful details in a structured order: examples, alternative tool, free endpoint, and cost. The bilingual repetition adds some redundancy, but the overall message remains tight and each clause carries substantive information, making it an efficient description.

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 simple two-parameter tracking tool with robust annotations, the description covers essential context: real-time query, no persistence, carrier list discovery, and the alternative tool for unknown carriers. It does not describe the response structure or error handling, but given the tool's straightforward nature and the support from annotations, this is only a minor gap and the description is largely complete.

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?

The schema covers both parameters with 100% description coverage, so the baseline is 3. The description adds extra value by listing concrete carrier code examples (cj, hanjin, lotte, etc.) and pointing to a free endpoint for the full list, which assists the agent in selecting valid values. It does not significantly enhance trackingNumber semantics but enriches carrier semantics enough for a score of 4.

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 clearly states the tool's function: 'Track a Korean parcel in real time by carrier code and tracking number.' It further distinguishes from the sibling tool 'parcel_tracking_auto' by explicitly noting that it should be used when the courier is unknown, eliminating ambiguity about the tool's scope.

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?

The description provides explicit guidance on when to use this tool and when to use an alternative: '택배사를 모르면 parcel_tracking_auto Tool로 자동판별 조회하세요' (If you don't know the courier, use the parcel_tracking_auto tool for automatic detection). It also suggests a free endpoint for the full carrier list, giving the agent a clear path to obtain valid carrier codes.

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