기동 검증

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

Goes well beyond the annotations: it does not alter the project, it downloads dependencies and a fixed Tomcat 10.1/11.0 build (sha256 verified, internal mirror EGOVFRAME_MAVEN_MIRROR preferred), stages the war under a temporary CATALINA_BASE, uses an empty port, and kills the process tree on completion. Timeout semantics ('first run includes dependency download') and the health-check rule (5xx means failure) are also disclosed.

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 is front-loaded in the first sentence, but the rest is a single dense paragraph that includes implementation internals an agent does not need for selection or invocation (Servlet version-to-Tomcat mapping, sha256 verification, mirror precedence, CATALINA_BASE mechanics). Those details crowd out the higher-value exclusions and failure taxonomy.

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 long-running, process-spawning tool this covers everything needed: preconditions, download behavior, cleanup, timeout, success criterion, and the structure of failure output (failure kind, offending bean name, config resource mapped back to project source, JDBC URL/driver, per-kind remediation). An output schema exists, so the description's extra explanation of the failure report is supplementary rather than a gap.

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 all six parameters, and the description mostly restates them (tomcatHome for closed networks, empty default port, actuator health path). It adds some operational framing — how port and path are used during the boot probe — but little syntax or constraint detail beyond the schema.

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 (launch the project and verify it actually boots, without modifying it) and enumerates the class of failures it targets — bean creation, config paths, DB connection, JDBC driver, MyBatis mapper XML — that compilation cannot catch. It explicitly excludes screen functional testing and production WAS (JEUS) startup, which cleanly separates it from test_egovframe_project and build_egovframe_project.

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?

Gives a clear when-to-use condition (runtime errors not caught by compilation) and explicit when-not exclusions (UI functional tests, production WAS startup). It also names the sibling tools to reach for on failure (prepare_egovframe_database, migrate_egovframe_project), so routing decisions are supported at both ends.

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