szlcsc_cache_status

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the cache is SQLite-based, it does not reveal whether clearing or pruning is destructive (e.g., irreversible data loss), the scope of the cache (global or user-specific), or any side effects.

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 relatively short, but the semicolon separation between actions makes it slightly harder to parse quickly. It could be clearer with bullet points or separate sentences.

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?

Given that an output schema exists, the description does not need to document return values. However, the tool has two parameters with distinct actions and no guidance on combining them; also, no examples or default behavior (e.g., what happens if no args are passed) is provided.

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 description adds meaning beyond the input schema by explaining the role of each parameter ('clear' empties cache, 'prune_days' cleans old entries). Since schema coverage is 0%, this is essential and well-done.

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 clearly states the tool is for viewing an SQLite request cache and specifies two distinct actions ('clear' and 'prune_days'), making the purpose clear. However, it doesn't explicitly differentiate from sibling tools, many of which also interact with cached or library data.

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?

The description implies when to use the parameters (e.g., 'clear=true' for clearing, 'prune_days=N' for pruning old cache), but provides no guidance on when not to use this tool versus alternatives like 'szlcsc_library_repair' or when to prefer cache operations.

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