CRUD 코드 생성

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds genuinely non-obvious behavior: it performs a full file-conflict check and writes NOTHING if any target file already exists (all-or-nothing atomicity). That is valuable context an agent cannot infer from the annotations. It stops short of describing permissions, overwrite semantics, or return payload, keeping it from a 5.

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 dense sentences, front-loaded with the generated artifacts first and the safety/atomicity behavior second. No filler, though the artifact enumeration and profile listing make the first sentence quite long. Efficient overall.

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 21-parameter generator with no output schema, the description establishes purpose, the two profile modes, and the all-or-nothing write policy — enough for an agent to select and invoke it safely. The absent output schema and lack of explicit return-format guidance are partially offset by the dryRun parameter documented in the schema, but the description itself could say more about generated file layout.

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 100% across all 21 parameters, so the schema already documents every field, enum, and default. The description adds high-level profile semantics (classic=Spring MVC+JSP vs boot=REST) and flags JSP/tests as optional, but no per-parameter detail beyond the schema. Baseline 3 is appropriate.

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?

Names a specific verb (생성/generate) and enumerates the exact artifacts produced (VO, Mapper XML, Service, Controller, optional JSP, optional JUnit 5 tests) plus the profiles supported. An agent can distinguish this from sibling generators like generate_egovframe_config, generate_egovframe_report, or apply_egovframe_recipe 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?

The description scopes the tool to the 'eGovFrame Development official CRUD wizard 입력 체계' and notes profile selection, which implies its usage domain. However, it never states when to prefer this over sibling scaffolding tools (create_egovframe_project, apply_egovframe_recipe) nor any preconditions/exclusions for calling it. Usage is implied rather than prescribed.

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