crbro_learn

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It discloses a key side effect: 'If the neuron (topic) does not exist, it will be created automatically.' This is valuable context beyond the parameter schema. It also mentions persistence across sessions. It does not disclose details like overwrite behavior or auth requirements, but for this simple storage operation, it is reasonably transparent.

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 two sentences, front-loaded with the primary action, then adds one key behavioral detail and a usage statement. Every sentence contributes to understanding without redundancy. It is concise and well-structured.

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 (6 parameters, 3 required, no output schema) and the lack of annotations, the description covers the essential context: what it does, when to use it, and a critical auto-creation behavior. It does not explain the return value, but no output schema makes that less critical. A minor gap is the behavior when a neuron already exists (update vs. append), which could be specified but is not a major omission.

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 already has 100% description coverage for all six parameters, so the baseline is 3. The description adds some semantic value by linking 'topic' to the concept of a neuron and enumerating the 'type' values in the first sentence. However, it does not add significant extra meaning for fields like domain, rationale, or confidence beyond what the schema already provides.

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 function with a specific verb ('Teach') and resource ('the brain'), and enumerates the types of knowledge it stores (fact, decision, pattern, preference). It also distinguishes itself from retrieval siblings by emphasizing persistence and storage. The phrase 'store knowledge that should persist across sessions' reinforces the purpose.

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 provides a clear usage directive: 'Use this to store knowledge that should persist across sessions.' This tells when to use the tool, implying that if persistence is needed, this is the tool. However, it does not explicitly mention alternatives like crbro_recall for retrieval or crbro_connect for relationships, so it lacks the explicit exclusion present in top-quality descriptions.

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