iv

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

The annotation readOnlyHint=true already declares the operation non-mutating; the description adds substantial context by listing the included diagnostics (first-stage F, Sargan/Hansen J, Kleibergen-Paap rk, Sanderson-Windmeijer, Hausman) and the statement 'Validation: certified parity evidence.' It also documents assumptions and pre-conditions that constrain valid usage. No contradiction with 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 long but well-structured: purpose first, then the method family list, diagnostics, validation, assumptions, and pre-conditions. The extensive method enumeration is necessary to convey the unified scopeasia. It front-loads the core purpose and avoids redundancy with the schema. A few phrases could be tightened, but overall it earns its length for a tool of this complexity.

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 is quite complete. It covers the tool's scope, the key methods, diagnostics, validation evidence, statistical assumptions, and pre-conditions for the formula. It points to 'the target function's docstring' for method-specific arguments, which is a reasonable delegation. Missing details like error behavior are not critical for a read-only estimation tool.

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 baseline is 3. The description does add some meaning for the `formula` parameter by specifying the parenthesised block syntax, but most parameter details (e.g., `robust`, `cluster`, `detail`) are already fully described in the schema. There is no significant additional semantic value for the parameters beyond what the schema provides.

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 'Unified IV estimation and the entry point for the whole IV family', clearly stating the verb and resource. It enumerates the specific estimator families (k-class, jackknife, lasso, mte, etc.), distinguishing this tool as the umbrella entry point rather than any one specific method. The phrase 'entry point' differentiates it from sibling tools like ivreg or lasso_iv without needing to open their schemas.

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 (relevance, exclusion, monotonicity) and pre-conditions ('formula includes the (endog ~ instruments) parenthesised block; at least as many instruments as endogenous regressors'), which help an agent understand when IV is appropriate. However, it never explicitly says 'use this tool instead of X' or 'for simple 2SLS with one method, consider a more targeted tool'. The routing to alternatives like ivreg or iv_diag is left implicit.

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