hebbrix_learning_insights

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

With no annotations provided, the description carries the full burden. It transparently discloses the tool's main behavior: returning posterior probabilities, credible intervals, evidence metrics, and observation counts. It also explicitly describes the conditional 'evaluate_readiness' mode with its refusal criteria, which is valuable behavioral detail. However, it does not explicitly state whether the tool has side effects (e.g., if it only reads data), though this is implied.

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 compact and efficiently structured. The first sentence states the core purpose, and the second sentence lists specific outputs and conditional behavior. Every word earns its place, with no filler or redundancy.

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 complexity (6 parameters, conditional mode, output schema), the description provides a solid level of completeness. It describes the returned values, the evaluate_readiness behavior, and refusal criteria. The main gap is missing explanations for 'actions' and 'collection_id', but the output schema and the rest of the description cover most needs.

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 description coverage is 0%, so the description must compensate. It adds meaning for policy_key ('one customer policy'), user_id/context ('this exact tenant/user/context'), and evaluate_readiness (with detailed behavior). However, it does not explain the 'actions' parameter or 'collection_id', leaving two parameters with only their titles for interpretation. This is a partial compensation.

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 opens with 'Explain what one customer policy has learned, with uncertainty,' which uses a specific verb and resource. It clearly distinguishes itself from sibling tools by focusing on learning insights for a single policy, complete with uncertainty quantification. The detail about posterior probabilities and credible intervals confirms the tool's specific 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 implies usage for inspecting the learning state of a specific policy in the context of a tenant/user/context. It clarifies the evaluate_readiness flag's conditional behavior. However, it does not explicitly state when to use this tool over alternatives like 'hebbrix_confidence' or 'hebbrix_ask', nor does it provide exclusions or prerequisites.

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