ipw

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

Annotations already declare readOnlyHint=true, and the description goes beyond by detailing assumptions, pre-conditions, failure modes, and typical minimum N. This adds meaningful context about the tool's internal logic and limitations, which is not captured by annotations alone.

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 information-dense yet well-organized with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical N). The core purpose is front-loaded, and every sentence contributes useful information without unnecessary 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?

The description covers assumptions, preconditions, failure modes, alternatives, and minimum sample size—all critical for a causal inference tool. Combined with the full parameter schema and output schema, the definition is nearly complete. The only gap is explicit when-to-use vs. specific alternatives, but that is partly addressed in the failure modes.

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%, so the schema already documents all 11 parameters. The description adds marginal value by contextualizing 'trimming' and the estimand choices, but it does not fundamentally enhance parameter understanding beyond the schema.

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 method (Inverse Probability Weighting) and target estimands (ATE/ATT/ATC) with propensity score trimming. It also names alternative tools (sp.tmle, sp.g_computation), though listing sp.ipw as an alternative to itself is slightly confusing. Overall, the purpose is 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 description provides assumptions (sequential exchangeability, positivity, model specification) and failure modes with suggested remedies (e.g., use TMLE when weights are extreme), which guide when IPW is appropriate. However, it lacks explicit 'use this when X, use alternative when Y' comparisons beyond the failure-mode hint.

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