warm_cache

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

With no annotations, the description carries full burden. It discloses that only memories not already in hot cache are promoted and requires a specific environment variable. This is good but could mention error behavior if the env is false or prediction fails.

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 concise with four sentences, each adding essential information. It starts with the main purpose, then clarifies scope, a constraint, and a prerequisite. No redundant text.

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 the tool's moderate complexity and presence of an output schema, the description covers key aspects: main action, constraint, and prerequisite. It could be slightly more complete with behavior on failure or env variable not set, but it is adequate for an agent.

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 parameter schema includes a basic description ('Memory ID to predict from'), and the description adds context by explaining that this ID is used for prediction and subsequent promotion. With 100% schema coverage, a baseline of 3 is appropriate, but the description adds value.

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's verb ('Pre-warm'), resource ('hot cache'), and specific action ('promotes predicted memories'). It distinguishes from sibling tools like 'promote' and 'predict_next' by focusing on predicted memories that are not already in 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?

The description implicitly suggests usage when predictive caching is needed and notes a prerequisite (env variable). However, it does not explicitly state when to use this tool versus alternatives like 'promote' or when not to use it.

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