tsf_cross_validate

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

Annotations already indicate readOnly, idempotent, non-destructive behavior. The description adds crucial behavioral context: runtime warning ('LONG-RUNNING'), output description (aggregated table, ranking, parquet path), and implicitly that it is safe but compute-intensive. This goes well beyond the annotations and aids agent expectations.

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 three short, purposeful paragraphs. The first sentence immediately states the tool's function. Each subsequent section (usage advice, output details, runtime warning) earns its place with no redundancy. It is front-loaded and efficient.

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's complexity (cross-validation, multiple models, windows, output schema exists), the description covers purpose, usage, baseline recommendation, output contents (aggregated metrics, rankings, prediction parquet), and runtime behavior. It is sufficiently complete for an agent to understand when and how to invoke the tool correctly.

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 nested input schema (CrossValidateInput) already provides parameter descriptions (e.g., models, metrics). The description adds high-level advice (like horizon matching the decision, baseline recommendation) but no new parameter-level semantics beyond what the schema offers. Schema coverage is effectively high despite the 0% top-level stat, so the description's incremental value here is moderate.

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-resource combination ('Compare models by rolling-origin cross-validation') and clearly distinguishes this tool from siblings like tsf_forecast (single model forecast) and tsf_list_models (model names). It states it replaces guesswork about model choice, making the purpose unambiguous.

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 gives explicit usage guidance: 'Always include SeasonalNaive as the baseline' and 'Start with statistical models on the real horizon before reaching for anything pretrained.' It also explains that the tool produces evidence for model selection. However, it does not explicitly state when not to use this tool (e.g., for final forecasts) or name alternatives, slightly reducing completeness.

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