tcai_curiosity

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

With no annotations, the description must carry the full burden of disclosing side effects and safety. It explains the internal computation, which is valuable, but it fails to state whether this is a read-only operation, what output it produces, or any side effects. This is a notable gap for a tool with no annotation coverage.

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 two sentences and front-loads the core concept. While dense with technical terms and a citation, it contains no fluff and every phrase contributes meaning. It remains compact and well-structured.

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?

No output schema exists, so the description should clarify return values or operational behavior. It does not mention output type, side effects, or when to use the tool, leaving the agent without key context for a moderately complex tool. The description is not complete enough for safe and correct invocation.

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 provides a complete description of the single parameter ('Representation vector (defaults to current broadcast)'), covering 100% of the schema. The description restates the default but adds no new semantics beyond that. Baseline 3 applies because the schema already does the heavy lifting.

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's purpose: computing intrinsic reward/curiosity via RND prediction error. It distinguishes itself from siblings by describing a specific mechanism (frozen target vs. online predictor) and its role as an exploration drive. However, it lacks an explicit action verb like 'compute' or 'calculate', slightly reducing clarity.

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?

No explicit when-to-use or alternative guidance is provided. The description mentions exploration drive and EFE but does not tell the agent when to choose this over sibling tools like wm_surprise or tcai_emotion_appraise. Usage is only implied, not stated.

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