AI 계층 조립

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

Goes well beyond the annotations by disclosing real behavioral traits: backups are created, removal restores originals, missing dependencies are inserted only inside marker sections, and any conflict causes a full abort with nothing written. It also notes dryRun needs no network. It does not describe the response/report shape, which keeps it off 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?

Four dense sentences, front-loaded with the outcome, then the mechanics, then the safety guarantee, then the preview tip. Every sentence carries information, though the parenthetical feature chain makes the first sentence heavy.

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 mutating, open-world assembly tool the description covers what is copied, what is merged, failure behavior, and the dry-run escape hatch, and annotations already carry the safety profile. What an agent still lacks is the result/report content and any prerequisite checks, but overall it is sufficient to call correctly.

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%, so every parameter (stack enum, ref, dryRun, includeUi/includeInfra/includeTests, projectDir) is already documented in the schema. The description reinforces dryRun and the UI/infra copies but adds no new syntax, defaults, or interactions beyond what the schema states, so the baseline 3 applies.

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 concrete verb+resource: assembling an official egovframe-ai-rag sample RAG chatbot (upload→embedding→hybrid search→LLM) into an existing Boot project, plus what gets copied (source, config, UI, infra) and the pom edit. It is clearly distinct from the generic add_egovframe_components in scope, but it never names that sibling to make the boundary explicit.

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?

Usage is implied by the context ('기존 Boot 프로젝트에 조립', egovframe-boot-starter-parent based) and there is a strong workflow hint to run with dryRun=true first. However, it gives no explicit when-to-use/when-not versus add_egovframe_components or reassemble_egovframe_components, and no stated prerequisites for the target project.

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