AGENTS.md 생성

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety class is known; the description adds the meaningful detail that existing files are protected behind an explicit overwrite gate and that dryRun is a non-writing preview. That is real added context about what would be destroyed. It does not describe the returned payload shape or failure modes when the project cannot be diagnosed, keeping it below 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?

Purpose is front-loaded in the first clause, and the em-dash content list is dense information an agent needs rather than filler. The single very long sentence with a nested comma list makes it slightly harder to scan, but nothing is redundant.

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?

With no output schema, the description carries the burden of explaining what comes back, and it does: file creation gated by overwrite, content-only return under dryRun. Combined with the itemized document contents and language options, an agent has enough to call it correctly. The one gap is that the success return value (written path versus raw content) is only implied.

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 the schema already documents lang, dryRun, fileName, overwrite and projectDir. The description only restates the overwrite and dryRun semantics and notes the Korean default/English option, adding no format or constraint detail (e.g. absolute-path expectation, filename pattern) beyond the schema. 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?

The description names a specific verb (진단해 ... 생성합니다) and a concrete artifact (AGENTS.md for Claude Code/Copilot/Cursor), then enumerates exactly what the document will contain. That is far beyond a tautology. It stops short of 5 because the '프로젝트를 진단해' framing overlaps with the sibling diagnose_egovframe_project, and the description never states how this differs from that tool's diagnostic output.

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 gives clear conditional usage rules: an existing file is refused unless overwrite=true, and dryRun=true returns content without writing — both are explicit when/when-not cues an agent can act on. It does not name any alternative tool (e.g. generate_egovframe_report or generate_egovframe_config) or say when to skip this one entirely, so it falls short of full alternative routing.

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