ivreg

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

With readOnlyHint=true, no mutation warning is needed; the description adds behavioral context by disclosing robust/clustered SEs and first-stage F diagnostics in the output. The 'Validation: certified parity evidence' note is a bit opaque but not contradicted by 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 compact and front-loads the estimator and syntax. The final 'Validation: certified parity evidence' sentence is vague and adds little operational value, preventing a top score.

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 an 8-parameter tool with a rich schema and an output schema, the description covers the core identity, the critical formula syntax, and the key diagnostics. It is slightly incomplete on clustering semantics and alternative-tool routing, but nothing essential to invoking the tool is missing.

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 coverage is 88%, so the schema already documents most parameters, and the formula example adds only slightly more meaning than the schema's own formula description. The claim of clustered SEs is not clearly mapped to any parameter such as robust, since the enum only lists hc1/hc2/hc3/nonrobust.

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 a specific estimator ('2SLS instrumental-variables regression') and its distinctive features (robust/clustered SEs, first-stage F diagnostics), which sets it apart from siblings like iv, iv_diag, and ivqreg. The formula template clarifies the resource being modeled.

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 formula syntax implies the intended use case: an outcome, exogenous regressors, an endogenous regressor and instruments. However, it does not explicitly state when to choose this over sibling IV-focused tools or when not to use it, so guidance is implied rather than made explicit.

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