clear_caches

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

The Korean text ('다음 도구 호출 때 다시 굽는다') adds an important behavioral consequence: caches are re-baked on the next tool call. This goes beyond the simple 'clear' statement and is valuable since no annotations are provided. However, this key behavior is only present in the Korean portion, and the English text omits it.

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 description is short but contains redundant bilingual text that is not identical. The English and Korean versions differ in content (English lacks the re-bake behavior and 'cache folders'), making it less clean and potentially confusing for an English-only reader.

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 parameters and an output schema present, the description covers basic purpose, but it leaves out usage guidance and hides a key lifecycle behavior in the Korean text. An agent could miss a significant consequence of calling this tool.

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?

The tool has zero parameters, so the description does not need to explain parameter meaning. The baseline of 4 applies and there are no ambiguities to compensate for.

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 states a specific action ('Clear baked caches') and a goal ('free disk space'), using a clear verb and resource. It is distinct from sibling tools like snapshot, restore, and reset_destroy, so an agent can differentiate it without opening schemas.

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?

No explicit guidance is given about when to use this tool versus alternatives. It mentions freeing disk space as a benefit, but there are no conditions, prerequisites, or exclusions to direct the agent's choice.

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