tcai_convergence

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

With no annotations, the description carries the full burden and delivers. It explains both modes (get/set), the exact halting condition (learning velocity high, curiosity/surprise low, stability sustained over patience cycles), and cites the source. This exceeds typical transparency for a configuration tool.

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?

Three sentences, front-loaded with purpose, then mode behavior, then halting logic. Every sentence adds value, with no repetition or filler.

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?

The tool has no output schema, and the description explains the no-arg return ('satisfaction state and active thresholds') but not the return for the with-arg mode. The halting condition is thoroughly described, and the schema covers all parameters. Minor gap on update response, but overall complete for a getter/setter.

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 description coverage is 100%, and each parameter has min/max/default in the schema. The description adds only a general reference to 'thresholds' and 'patience cycles' but doesn't add 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 the tool's dual function: inspect or configure the halting criterion. It specifies the resource ('recursive double-loop halting criterion') and distinguishes it from siblings by explicitly tying it to tcai_cycle's stopWhenSatisfied. The verbs 'inspect or configure' are specific and action-oriented.

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 clear context on when to use the tool: with no arguments for inspection, with arguments for updating thresholds. It also explains the halting condition, offering the agent a decision framework. However, it does not explicitly exclude alternative tools or state when not to use it, but the context is sufficient.

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