tcai_convergence

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

With no annotations, the description carries the full burden of transparency. It discloses the dual get/set behavior, the exact multi-criteria halting condition (free energy, task quality, epistemic value, patience), and explicitly notes that stationarity alone is insufficient. This is rich behavioral context, though it omits details about persistence or effects of updates.

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 long and front-loaded with 'Inspect or configure', immediately stating purpose. Every clause contributes meaningful information: modes, halting condition, and a qualifying note about stationarity. No wasted words or repetition of schema details.

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 the tool has no output schema and no annotations, the description covers the query mode (returns state and thresholds) and the full halting logic, which is the tool's core complexity. It does not describe the exact return format, but that is a minor gap for a configuration tool with well-schemaed parameters.

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?

Schema coverage is 100% with descriptive parameter names and defaults, so the baseline is 3. The description adds value by showing how the parameters interrelate in the halting condition (e.g., all conditions must be sustained over patience cycles), which goes beyond the individual parameter descriptions and clarifies their combined semantics.

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 uses a specific verb 'Inspect or configure' with a clear resource 'recursive double-loop halting criterion (v2.9)', immediately distinguishing it from sibling tools like tcai_metrics or tcai_memory_retrieve. It also clearly defines two modes of operation (no args = query, with args = update), leaving no ambiguity about what the tool does.

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 explains exactly when to call it: with no arguments to retrieve the current satisfaction state and thresholds, and with arguments to update them. It also states the full halting condition, giving context for when this tool would be relevant. However, it does not explicitly name alternative tools or provide exclusion criteria, so it falls short of a 5.

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