clean_cache

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

With no annotations, the description carries the full burden, and it discloses what each target destroys (prediction history, temp frame dir, everything) and the purpose of freeing disk. It does not address reversibility or required permissions, but for a cache-clean operation the destruction profile is reasonably clear.

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?

Structured into 入参/返回/用途/下一步 with the core action front-loaded; every section adds actionable information and nothing is padding.

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?

A single-optional-param tool whose parameter meanings, effects, and follow-up steps are all documented, and return values need not be explained since an output schema exists. Nothing needed to call it correctly is missing.

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 coverage is 0% and the schema does not even declare the enum, so the description's documentation of all (default) / predict / frames with meanings is the only source of parameter semantics. It fully compensates for the schema gap.

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+resource ('清理运行期缓存') and enumerates exactly what each mode clears, so an agent knows the scope. It does not explicitly differentiate from the sibling reset_predictor, which sounds related to the 'predict' target, leaving mild ambiguity about which tool to reach for.

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 concrete when-to-use conditions: free disk after long runs, keep prediction data clean before switching rounds, and clear frames before long sessions. It does not state when NOT to use it or compare directly to reset_predictor, so it stops short of full routing guidance.

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