check_multicollinearity

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

With no annotations, the description carries full responsibility for behavioral disclosure and does so excellently. It specifies concrete thresholds (VIF>10 problematic, VIF>5 moderate, |r|≥0.8 for grouping), states that ID-like unique columns are skipped, caps at 50 numeric columns, and notes 'Output size: small'. These details go far beyond generic expectations and set clear behavioral 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 concise and well-structured. The first line states the core function in a compact summary, followed by bullet-like details that are easy to parse. Every sentence adds value without wasted words, and key constraints are front-loaded.

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?

For a check tool, the description covers the essential behavior, thresholds, limits, and output size. An output schema is present, so return values are presumably documented elsewhere. The main missing piece is the interaction with the columns parameter, which would clarify whether the analysis applies to all numeric columns or only those selected. This is a minor gap given the overall richness.

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 schema has two parameters (source_id and columns) with 0% schema description coverage, so the description must compensate. However, the description never explains what these parameters are or how to use them. While it mentions 'columns' behaviorally (e.g., 'Caps at 50 numeric columns'), it does not clarify that the columns parameter restricts the analysis to selected columns or what happens when it's null. This leaves a significant gap for an agent selecting and invoking the tool.

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 explicitly states the tool performs Variance Inflation Factor (VIF) and correlated-group detection, which is a specific verb+resource combination. It distinguishes itself from sibling tools like check_correlations by focusing on multicollinearity and providing detailed behaviors (VIF thresholds, grouping at |r|≥0.8). This makes the tool's purpose unmistakable.

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 usage context is implied through the description (e.g., multicollinearity detection for regression modeling) but no explicit comparison to alternatives is given. It does not say when to prefer this tool over check_correlations or other check tools, nor when not to use it. The phrase 'Level 3' is cryptic and provides no actionable guidance.

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