tcai_meta_learning

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

No annotations are provided, so the description must fully disclose behavioral traits. It indicates reading state and optional injection, but does not explain side effects of injection (e.g., whether it permanently alters internal state) or whether the tool is read-only by default. Minimal disclosure.

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 concise (two sentences) and front-loaded with the tool's purpose. It includes useful interpretation of outputs. No wasted 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?

Given no output schema, the description adequately describes output states. However, it lacks context on how this tool fits into the broader tcai workflow or what happens after injection. Completeness is adequate for a simple state query but could be improved.

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 describes the only parameter 'rpe' as injecting a reward-prediction-error sample. The description adds context about output interpretation but doesn't enhance parameter understanding beyond the schema. With 100% schema coverage, baseline 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 states it reads meta-learning state (velocity and novelty spike) and optionally injects RPE. However, it does not explicitly distinguish this tool from siblings like tcai_convergence or tcai_curiosity, which might have overlapping 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 interprets output states ('velocity>0 ⇒ converging; noveltySpike ⇒ novel/confusing regime') but provides no guidance on when to use this tool versus alternatives. For example, it doesn't specify whether to use this before or after tcai_active_inference or tcai_cycle.

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