tcai_active_inference

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

With no annotations, the description carries the transparency burden. It explains the conceptual meaning of the telemetry values and their principled nature, but it does not explicitly state whether the operation is read-only, if it has side effects, or if it requires specific system state. The term 'telemetry' implies a read, but operational details beyond output semantics are missing.

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, with the main point front-loaded ('Active-inference core telemetry') followed by a precise, colon-separated list of contents. The second sentence adds essential context (halting criterion, principled vs. heuristic) without waste. Every clause earns its place.

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 and no annotations, the description provides rich conceptual context by naming and explaining each telemetry field (F, G(π), task quality, entropy, action) and its role in halting. It stops short of specifying the exact return format, units, or data types, which would make it fully complete for an agent.

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 tool has 0 parameters, so the baseline is 4 per the rubric. The description adds no parameter info because none exist, but it enriches the understanding of what the returned data means, which is useful for interpreting the output.

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 'Active-inference core telemetry' and lists specific quantities (F, G, task quality, entropy, action), making the resource and scope clear. It distinguishes itself from heuristic correlates by stating it is the 'principled quantity' for halting, but lacks an explicit verb like 'get' or 'return', which keeps it from a 5.

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 explicitly states this telemetry is what the halting criterion thresholds on, providing a clear when-to-use scenario. It also says 'not a heuristic correlate', implying it should be preferred over heuristic metrics, though it does not name specific alternative tools.

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