variance_filter

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

With no annotations provided, the description carries the full burden. It explicitly states the tool is non-destructive, returns a list, and does not auto-drop. The example further clarifies threshold usage. It does not disclose edge cases (e.g., behavior with zero-variance vs near-zero), but for a simple filter tool this is adequate.

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 efficient, front-loaded with the main action, and includes a return type, a non-destructive note, a rationale, and a concrete example. Each sentence earns its place, with no 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 simplicity, an output schema exists, and the description covers core behavior, non-destructive nature, and threshold semantics. It lacks an explanation of df_name and does not explicitly differentiate from correlation_filter, but overall it is sufficient for a 2-parameter tool.

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 explains the threshold parameter via 'variance at or below threshold' and the example with threshold=0.01. However, the df_name parameter is never described, leaving its role unclear. The description only partially compensates for the lack of schema documentation.

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 function: it identifies columns with variance at or below a threshold and returns a list of low-variance columns. It also explicitly mentions 'Does NOT auto-drop' to distinguish it from drop operations like drop_columns or drop_low_importance.

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 by noting low-variance columns are constant/near-constant and 'provide no useful information for modeling.' It implies use for feature inspection before dropping, and 'Does NOT auto-drop' hints at the alternative of using drop tools, though it does not explicitly name them.

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