출근/퇴근 기록 저장

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, and the description reinforces this by calling the action '되돌릴 수 없는 기록' while adding a human-in-the-loop approval rule that the annotations cannot express. It does not say what the server returns or what happens on an expired/invalid token, so it stops short of full behavioral coverage.

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?

Two tight sentences, front-loaded with the action and its token source, then the safety gate. No redundant restatement of the title or the annotations.

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 one-parameter commit tool with rich annotations, the description covers purpose, prerequisite, and irreversibility, which is nearly all an agent needs. The only gap is the absence of any return/outcome signal, which matters because no output schema is provided.

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?

There is a single parameter with 100% schema description coverage, and the schema already says the token comes from jade_prepare_punch, so the description adds no syntax, lifetime, or failure semantics beyond the structured field. Baseline 3 applies when the schema does the parameter work.

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 names a specific verb and resource ('출근/퇴근을 실제 JADE 근태에 기록한다') and ties the input to the producing sibling jade_prepare_punch, which cleanly separates this commit step from the prepare step and from sibling commit tools like jade_commit_vacation or jade_commit_remote_work.

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?

It states an explicit precondition for invoking: the user must have seen the preview and explicitly approved. That is a concrete when-to-use gate plus an implicit when-not (no approval, no call), which is exactly what an agent needs before a one-way write.

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