ypollak2/llm-router

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

With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Clear' implies destruction, the description lacks critical safety context: whether the operation is permanent, if it affects other users, performance implications, or required permissions.

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 a single, efficient sentence of five words with zero redundancy. It is appropriately front-loaded and sized for a zero-parameter tool.

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?

While the output schema handles return values and the parameter schema is trivial, the description is incomplete for a destructive operation. It lacks scope boundaries (does it clear all entries or user-specific ones?) and safety prerequisites that would guide proper invocation.

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 input schema contains zero parameters, triggering the baseline score of 4. There are no parameters requiring semantic clarification 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?

The description uses a specific verb ('Clear') and identifies the exact resource ('prompt classification cache'), distinguishing it from sibling tools like llm_cache_stats (which likely reads stats) and llm_classify (which likely uses the cache).

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 on when to use this tool versus alternatives, nor any warnings about when NOT to use it (e.g., during active classification operations). The description states what it does but not why or when an agent should invoke it.

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