5.x 전환 리허설 (사본에서 실측)

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

Annotations set readOnlyHint=false, destructiveHint=false, idempotentHint=true; the description adds substantial context beyond them: it writes only to EGOVFRAME_CACHE_DIR/rehearsal, excludes build artifacts/VCS/backups, verifies original immutability via pre/post directory fingerprints, removes the 100-error javac cap, and keeps the workspace only when keepWorkspace=true. This is rich disclosure that is fully consistent with the 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?

The purpose and the copy-only guarantee are front-loaded, and the long middle is organized as a numbered (1)-(4) sequence that mirrors the steps parameter. It is dense and slightly run-on but each clause carries distinct operational information.

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 multi-stage, mutating, long-running tool it covers what gets created, where, what is excluded, the two compile passes, immutability verification, and what output to expect, and an output schema already exists so return values need no further explanation.

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 100% and an output schema exists, so the baseline is already met; the description goes further by mapping the numbered steps (1)-(4) onto the steps enum, noting the order is fixed, and clarifying what sourceTag=auto means. It does not explain topN or format beyond the schema, so it stops short of full parameter elaboration.

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 ('5.x 전환을 미리 돌려 봅니다') with the operative scope: run on a copy without touching the project. This clearly separates it from the sibling migrate_egovframe_project (real migration) and reassemble_egovframe_components, and an agent can distinguish them 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?

'프로젝트를 건드리지 않고 사본에서' establishes the rehearsal-before-migration context and the safety prerequisite clearly. It never names migrate_egovframe_project as the alternative once the rehearsal is done, so the when-to-use is strong but not fully enumerated with exclusions.

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