stepwise

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

The readOnlyHint annotation already communicates that the operation is non-mutating, so the description's bar is lower. The added 'Validation: validated evidence tier' sentence is a vague meta-property rather than a behavioral disclosure about side effects, output granularity, or constraints. It does not contradict the annotations, but it also does not meaningfully expand beyond them.

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 first sentence is concise and front-loaded with the core purpose. The second sentence about validation evidence tier is tangential and does not clearly earn its place for an agent deciding how to invoke the tool, making the structure slightly wasteful despite the overall short length.

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?

This is a 13-parameter tool with enums, chaining via result_id/as_handle, and multiple selection criteria, yet the description provides only a one-line purpose and a validation note. Although the schema is thorough, the description omits an overview of the selection process, when to use different criteria, and how chaining works, leaving the contextual picture incomplete.

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 100%, with every parameter (data_path, x, y, detail, method, criterion, etc.) already explained in the input schema. The description adds no parameter semantics of its own, so the schema carries the full burden and the baseline of 3 applies.

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 states a specific operation—'Stepwise variable selection'—and a target model type, 'OLS regression,' so an agent can tell it performs iterative variable selection rather than a plain fit. However, it does not explicitly distinguish itself from sibling selection tools like lasso_select or rlasso, so it misses the full sibling-differentiation bar.

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?

No guidance is provided on when to use this tool versus alternatives such as lasso_select, rlasso, or regress. There is no mention of use cases, exclusion criteria, or relationships to sibling methods, leaving the agent to infer appropriateness from the name alone.

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