find_drivers

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

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds behavioral details: it performs correlation analysis, returns r, p-value, R², and a ranked list, and limits candidates to 30. This supplements the annotations without contradiction, though no information about potential side effects or permissions is needed given the annotations.

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 core purpose. The term 'KILLER ANALYSIS' adds a slight attention-grabbing tone but does not detract from clarity. Each sentence adds value: defining the task, use case, output, and constraint. It could be slightly tightened but remains effective.

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?

The description covers the main functionality, output format, and constraint. However, it does not explain the optional time parameter or provide details on how results are ordered (e.g., by r or p-value). Given no output schema, more detail on the return structure would improve completeness. The presence of annotations partially compensates, but the missing time parameter guidance is a gap.

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 description clarifies the roles of target_indicator and candidates, and adds the constraint of maximum 30 candidates, which goes beyond the schema descriptions. However, the 'time' parameter lacks description in both schema and description, leaving its purpose unclear. With 75% schema coverage, the description provides meaningful additional context for the core parameters.

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 ranks candidate indicators by correlation strength to predict a target KPI. It uses specific verbs (rank, predict) and identifies the resource (candidates). It distinguishes itself from sibling tools like 'correlate' and 'regression' by focusing on ranking multiple candidates rather than single correlation or regression.

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 targets 'what moves my KPI?' questions and sets a maximum of 30 candidates per call, providing clear context. However, it does not explicitly mention when not to use this tool or suggest alternatives like 'correlate' for simple correlations or 'regression' for modeling, so it lacks full exclusion guidance.

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