tcai_curiosity

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

With no annotations, the description must disclose behavioral traits like return type, side effects, or state requirements. It discusses the conceptual algorithm and default behavior but fails to state whether this is a read-only computation, whether the online predictor is updated, what the output looks like, or any edge-case behavior. This is a significant gap for an unannotated tool.

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?

Three sentences, front-loaded with the core purpose, each sentence provides distinct value: algorithm, interpretation, and default behavior. No filler or repetition.

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 is conceptually explained (RNDCuriosity, novelty, EFE proxy) and the default input is stated, which is helpful. However, with no output schema, the description omits the return value format (likely a scalar but unstated) and any side effects or dependency on internal state (e.g., whether the online predictor is updated), making it incomplete for operational use.

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 already fully describes the single 'embedding' parameter ('Representation vector (defaults to current broadcast)'), and the description echoes this default. The description adds a bit of conceptual context (prediction error on representation vector) but doesn't alter parameter meaning, so the baseline score of 3 applies given 100% schema coverage.

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 computes intrinsic reward/curiosity via RNDCuriosity prediction error, using the term 'RNDCuriosity port' and explaining the meaning (high error = novelty). This distinguishes it from sibling tools like tcai_active_inference or tcai_meta_learning, which have different purposes.

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 by saying it 'Defaults to the current GNW broadcast', indicating a common no-argument invocation, but it does not explicitly state when to prefer this tool over alternatives or any exclusions. No alternative tools are mentioned.

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