get_registration_status

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds real behavior beyond them: an implicit cap of 10 results when no id is supplied, and the fact that warnings and failure causes are surfaced rather than just a status code. Auth and pagination behavior remain unstated.

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?

A single dense sentence that front-loads the scope (one job vs. recent 10) and then the returned content, with no filler or redundancy. Every clause carries information an agent needs.

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?

Given an output schema exists, return values need not be detailed, and the annotations cover the safety profile. For a one-optional-param read tool the description is essentially complete, though it omits how job_id is produced and any polling guidance that would make the workflow self-contained.

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 description coverage is 0% for the single job_id property, so the description must carry the load, and it does: job_id selects one job and its absence switches to the 10-recent-jobs mode. It does not state the id's format or where an agent obtains it (presumably from register_product), which keeps it from 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 ('조회한다' + '등록 작업') plus the return content (단계·경고·실패 원인) and the two operating modes (single job vs. recent 10). An agent can distinguish it from the sibling register_product, which performs the registration rather than reporting on one. It stops short of naming a sibling explicitly, which is what a 5 would require.

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 conditional '하나 또는 최근 10개' conveys clear usage context: pass job_id for a specific job, omit it for a recent-jobs overview. There is no explicit statement of when this tool should be reached for (e.g., polling after register_product) and no exclusion/alternative routing, so it falls short of a 5.

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