tsf_forecast

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the bar is lowered. The description adds valuable context: the full forecast goes to parquet, the response carries path/column list/row count/preview, warns against raising max_preview_rows, and flags 'LONG-RUNNING for foundation models' — all beyond what annotations provide. No contradictions with annotations (readOnlyHint=true is consistent with generating forecasts without mutating data).

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 very concise: a terse three-sentence explanation that front-loads the core action, then adds usage guidance and behavioral warnings. Every sentence adds essential information without fluff.

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 (forecasting with multiple models and intervals), the output schema exists, so return values don't need elaboration. The description covers the critical workflow (use after cross-validation), output format (parquet with preview), and a key gotcha (don't dump full frame). It lacks explicit error conditions or prerequisite checks, but for the scope, it is largely complete.

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%, meaning the schema provides no parameter descriptions — so the description must compensate. Although the main description does not detail parameters, the parameter `max_preview_rows` receives meaningful context: 'Rows of the forecast to inline... read that instead of raising this.' Other parameters (handle, models, h, level) have descriptions in the schema via the JSON Schema, but since coverage is 0% (likely meaning no separate param list in the description), the main text does not clarify their meaning beyond what the schema already provides. Baseline 3 is appropriate as the description adds some context for max_preview_rows but not for others.

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 that the tool fits on full history and forecasts h periods ahead with intervals. It uses specific verbs like 'fit' and 'forecast' and explicitly identifies the resource as the time series forecast. However, it does not directly differentiate from siblings like tsf_cross_validate, though the usage guideline addresses that.

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 explicitly says 'Use after tsf_cross_validate has justified the model choice,' providing clear sequencing context and an alternative (cross-validation). It does not mention when not to use it or list specific alternatives for other tasks like anomaly detection, but the primary usage guidance is strong.

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