cache_set

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

No annotations provided. Description only says 'store in cache' with no details on overwriting, key generation, idempotency, or caching policy. Agent lacks critical behavioral info.

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?

Two sentences, front-loaded with action and use case. No wasted words, though could briefly mention key generation without bloat.

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?

Adequate for a simple cache write with no output schema, but missing overwrite behavior and key formation details that would help agent avoid unintended overwrites.

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 50% with only 'response' and 'provider' described. The description adds no extra meaning to 'messages' or 'model' beyond implied role. Agent cannot infer how keys are formed.

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?

Clearly states 'Store an LLM response in the cache' with a specific verb and resource. Distinguishes from sibling cache_get (retrieve) by context.

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?

Explicitly says 'Call this after receiving a response to avoid re-paying for identical future requests', providing clear usage context. Doesn't mention when not to use, but siblings are distinct enough.

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