tcai_curiosity

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

The description explains the mechanism (prediction error between frozen target and online predictor) and default behavior (uses current GNW broadcast). No annotations are provided, so the description carries the full burden. It does not mention side effects, return format, or resource implications, which is a gap.

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 (two sentences) and front-loads the key concept. The first sentence is dense with jargon but efficient. It earns its place without unnecessary information, though could be slightly more streamlined.

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 description lacks information about the output (likely a scalar curiosity value), which is critical since no output schema exists. It also does not clarify whether the tool modifies any state or is purely read-only. Given the technical complexity and absence of annotations, these omissions reduce completeness.

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?

With 100% schema description coverage, the schema already documents that 'embedding' is a representation vector defaulting to current broadcast. The tool description adds no additional meaning beyond what the schema provides, so baseline of 3 is appropriate.

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 computing an intrinsic-reward/curiosity signal based on prediction error, with a specific algorithm (RNDCuriosity) and purpose (exploration drive proxy for EFE). It differentiates from sibling tools like tcai_active_inference by focusing on novelty detection. However, the verb (e.g., 'computes') is implied rather than explicit.

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 does not provide explicit guidance on when to use this tool versus alternatives (e.g., tcai_self_model, tcai_metaconsciousness). It mentions it serves as an epistemic value proxy but lacks when-to-use or when-not-to-use criteria, leaving the agent to infer usage from context.

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