hebbrix_choose_action

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

With no annotations provided, the description carries the full burden and does so thoroughly. It reveals that the first action is the safe baseline, that only authorized actions are allowed, that exploration_rate is capped at 0.2, that missing outcomes are censored rather than counted as failures, and that action_probability is required with multiple actions. These are meaningful behavioral traits not obvious from the schema.

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 long but appropriately so for a complex 10-parameter tool. It is front-loaded with the core purpose, then organized into usage modes, parameter semantics, and the required outcome-reporting follow-up. Every sentence provides operational value; there is 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, an output schema, and rich parameter/behavioral details, the description is complete. It explains the full decision lifecycle—record, perform, report—and covers safety constraints, exploration, and outcome censoring. Optional parameters like user_id and collection_id are conventional and don't need elaboration.

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%, but the description compensates by defining the key parameters: policy_key identifies the decision type, actions are stable machine keys, context should only contain factors that affect the decision, baseline_action overrides the first action default, and chosen_action/action_probability/exploration_rate are explained with usage rules. The remaining optional parameters (user_id, collection_id, idempotency_key) are conventional and self-explanatory from their names.

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 a specific, non-tautological statement: 'Choose and RECORD an action before its result is known.' It clearly identifies the resource (an action decision) and distinguishes the tool's role from the outcome-reporting sibling by instructing the caller to later call hebbrix_report_outcome.

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 gives concrete usage context: 'Use for repeatable decisions whose real outcome can be reported later,' and it contrasts normal use (omit chosen_action) with logging an external choice (pass chosen_action). It also sets an explicit constraint on exploration_rate. However, it does not explicitly name alternative tools or state when not to use this tool versus siblings like hebbrix_log_decision.

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