check_feature_signal

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

With no annotations, the description carries the full burden. It discloses the exact statistical methods (Pearson/Spearman, ANOVA/η², χ²/Cramér's V, Welch t-test/Cohen's d) and the output format (ranked features with effect sizes and strength buckets). This goes beyond a generic statement and provides meaningful behavioral insight, though it does not cover edge cases or potential side effects.

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 concise and front-loaded with the main purpose. The subsequent sentences efficiently list the type-pair test selection and output summary, with no redundant or filler content. Every sentence adds value.

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 and the presence of an output schema, the description adequately covers the methodology and return values. It mentions pairing with auto_modeling_audit and explains the strength buckets. The only gap is the lack of explicit source_id description and potential edge cases, but overall it is sufficient for an experienced user.

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 explicitly defines target_column as the column relative to which features are scored. source_id is not mentioned, but its name strongly implies the dataset identifier. With only two parameters and one clearly explained, the description provides partial compensation but not full clarity for both.

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 opens with 'Score every feature for signal strength relative to target_column,' which clearly identifies the action (scoring features), the resource (features), and the target. It distinguishes itself from sibling tools by detailing specific statistical tests for each type pair, making it unique among check_* tools.

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 for when to use this tool (e.g., to score feature signal against a target) and mentions it pairs with auto_modeling_audit. However, it does not explicitly state when not to use it or name alternative tools like check_correlations or check_multicollinearity, so it lacks explicit exclusions.

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