causal

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

With readOnlyHint=true already covering the safety profile, the description adds the key orchestration behavior: automatic diagnosis, estimator recommendation, fitting, robustness checks, and result return. It does not mention caching side effects, but as_handle's own parameter description covers that, and there is no conflict with 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 two tight sentences with the pipeline front-loaded and no filler. Every phrase earns its place by specifying what the tool does and when to use it.

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 a 15-parameter orchestration tool, the description is a good overview but does not state the minimum invocation pattern (e.g., data_path or result_id plus y and treatment) or that results can be chained via result_id. The output schema and parameter descriptions fill some gaps, but the main text leaves invoke-critical prerequisites implicit.

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 only 40% and the description contributes no parameter-level semantics. Parameters like y, treatment, design, cohort, time, and id are left to inference from names, and the description does not clarify which inputs are essential or how they combine. With low schema coverage, the description fails to compensate.

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 concrete end-to-end workflow ('diagnose -> recommend estimator -> fit -> run robustness -> return result') and explicitly labels itself the one-shot entry point. This distinguishes it from stage-level siblings like diagnose or recommend without needing to inspect 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?

It clearly communicates to use this tool when the agent wants the full causal pipeline in a single call, framing the alternative as manually orchestrating stages. It does not name specific sibling tools or give exclusion criteria, but the one-shot phrasing provides enough context for selection.

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