Run rolling time-slice cross-validation to evaluate out-of-sample predictive accuracy (RMSE/NRMSE) across multiple temporal folds for a fitted marketing mix model.
Run rolling Time-Slice Cross-Validation with PyMC-Marketing. Evaluates out-of-sample predictive RMSE/NRMSE across multiple temporal folds.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral burden. It does disclose that the operation runs multiple temporal folds and evaluates out-of-sample predictive RMSE/NRMSE, which is useful. However, it remains silent on side effects, computational cost, whether the model must already be fitted, and the exact return structure.
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 tight and front-loaded: two sentences, no filler, with the primary action stated first. The second sentence adds meaningful outcome information without redundancy.
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 annotations, no output schema, and a wrapped input object, the description is too thin for safe autonomous invocation. An agent would need to infer that model_id is required and would have no clear idea what the returned RMSE/NRMSE artifact looks like or when this evaluation is appropriate.
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 description never references model_id, n_init, step_size, forecast_horizon, or sampler settings, and schema description coverage is reported as 0%, so the description was expected to compensate. The phrases 'rolling' and 'temporal folds' only vaguely hint at fold-related parameters and do not clarify the required fitted model ID.
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 is specific: 'Run rolling Time-Slice Cross-Validation with PyMC-Marketing' names a clear verb and resource, and it states the evaluation outcome (out-of-sample RMSE/NRMSE across temporal folds). This distinguishes it from sibling tools like fit_mmm, diagnose_mmm, or evaluate_prior_sensitivity.
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 no guidance on when to use this tool versus alternatives such as diagnose_mmm, evaluate_prior_sensitivity, or calibrate_mmm. It also does not state prerequisites such as requiring a successfully fitted model before cross-validation can run.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.