tcai_curiosity

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

No annotations are provided, so the description carries the full burden of disclosing side effects and state changes. It explains the computation and the default broadcast source but does not state whether the tool is read-only, whether the predictor is updated, or what the return value is. This is a significant transparency gap for a tool that may have internal state.

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, front-loaded with the core concept, and efficiently conveys the algorithm, interpretation, and default. The use of jargon (RND, EFE, GNW) adds density but does not waste words.

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?

The tool has no output schema and only one optional parameter, yet the description does not explain the return format (e.g., a scalar value). It provides good conceptual context but leaves out practical details about what the agent can expect as a result, making it adequate but incomplete.

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 schema covers 100% of parameters, with the 'embedding' property described as 'Representation vector (defaults to current broadcast)'. The description reinforces the default behavior but adds no new semantic information 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 identifies the tool as an intrinsic-reward/curiosity mechanism based on prediction error, referencing RNDCuriosity and explaining the high-error-equals-novelty relationship. It distinguishes itself from sibling tcai tools by its specific algorithm and purpose, though it lacks an explicit verb like 'computes' or 'returns'.

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 exploration or novelty-seeking ('exploration drive (EFE epistemic value proxy)') but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions. The usage context is present but not fully articulated.

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