Calculate Lyapunov convergence for a chain-of-thought trajectory to classify reasoning as stable or chaotic and flag potential hallucination.
Calculate Lyapunov Convergence of a trajectory (Chain of Thought). Returns a JSON object {lyapunov_exponent, classification: 'stable'|'chaotic'} - negative result means stable/converging, positive means chaotic/hallucinating.
| Name | Required | Description | Default |
|---|---|---|---|
| curvature | No | ||
| trajectory | Yes |
Changes observed during successful MCP inspections.
v4.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose the return object and the sign-based interpretation (negative = stable/converging, positive = chaotic/hallucinating), which is genuinely useful behavioral context, but it says nothing about input format expectations, cost, or what the `curvature` setting changes.
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?
Two tight sentences: the computation first, then the returned fields and their interpretation. Nothing is wasted and the key semantics (sign meaning) are front-loaded.
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?
With no output schema, the description does cover the return values well. However, for a tool whose only required parameter is an undocumented nested numeric array plus an unexplained `curvature` option, the agent still lacks enough information to construct a correct call.
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 0%, so the description must compensate. It adds real meaning for `trajectory` (a Chain of Thought), but never explains that it is an array of numeric vectors or what those vectors should be, and `curvature` is entirely unaddressed.
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 states a specific verb and resource ('Calculate Lyapunov Convergence of a trajectory'), names the domain concept (Chain of Thought), and even reports the return payload shape. It is clearly distinguishable from analytic siblings such as hyperspace_analyze_geometry or hyperspace_predict_momentum.
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?
Usage is only implied: an agent can infer the tool is for judging whether a reasoning trace is stable or hallucinating, but there is no explicit 'use this when / not when' or comparison against alternatives like hyperspace_verify_generation or hyperspace_predict_momentum.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.