tcai_meta_learning

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

With no annotations, the description carries the full burden. It discloses the meaning of velocity and noveltySpike and notes that an RPE sample can be optionally injected, which implies a side effect. However, it does not clarify the full effects of injection, whether reading is side-effect-free, or any error conditions.

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, with no filler. It packs state interpretation and optional action into a tight structure, front-loading the primary purpose.

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 there is no output schema, the description does not explicitly state the return format or structure, though it hints at velocity and noveltySpike fields. It also doesn't elaborate on the consequences of injecting an RPE sample. For a somewhat complex state tool, this is 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 input schema already provides 100% coverage for the single 'rpe' parameter with a clear description. The tool description adds the word 'inject' and reinforces the sample semantics, but does not add significant new meaning beyond the schema. 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 exposes meta-learning state, specifically learning velocity from RPE-variance dynamics, with interpretation for velocity and noveltySpike. It also mentions optional injection of an RPE sample. This goes beyond a tautology and gives a specific resource and action, though it doesn't explicitly name a verb like 'get' or 'read', it's clear enough.

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 provides useful interpretation cues ('velocity>0 ⇒ converging; noveltySpike ⇒ novel/confusing regime') that implicitly tell when this state is relevant, but there is no explicit guidance on when to use this tool vs. siblings like tcai_convergence or tcai_curiosity, and no mention of exclusions.

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