principal_strat

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

Annotations only provide readOnlyHint=true, so the description carries the behavioral disclosure burden. It goes well beyond the annotation by documenting known limitations, failure modes, assumption requirements, and the fact that the instrument path ignores method and reports only tau_Y and tau_S. No contradiction with annotations is present.

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 and front-loaded with purpose, followed by labeled sections for validation, limitations, assumptions, preconditions, and failure modes. Most sentences earn their place; the 'Validated evidence tier' phrase is somewhat cryptic and the failure-mode sentence appears truncated, so it is not perfectly concise.

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 complex causal-inference tool, the description is remarkably complete: it covers identification strategies, assumptions, preconditions, limitations, and failure behavior, while the schema handles parameter details. It falls short of a 5 because the failure-mode sentence is cut off and it never explains the 'validated evidence tier' concept or how it should affect an agent's invocation.

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 100%, so the baseline is 3. The description adds meaningful method-level semantics for method, covariates, and instrument beyond the schema's short labels, such as what each identification strategy actually computes. It does not elaborate on all 15 parameters, but the schema already documents those adequately.

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 clearly states the tool's purpose: principal stratification estimation, with two named strategies and specific outputs (complier PCE/LATE, Zhang-Rubin bounds on always-survivor SACE, Ding-Lu stratum-specific effects). It does not explicitly differentiate from adjacent sibling tools like survivor_average_causal_effect or selection_bounds, so it stops short of the top score.

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 gives concrete guidance on when to use each method: monotonicity versus principal_score, the need for covariates under principal_score, the AIR/Wald LATE path when an instrument is supplied, and relevant assumptions and preconditions. It does not name sibling tools or exclusion conditions for preferring another estimator, so it lacks the explicit 'when-not-to-use-this' routing of a 5.

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