distributional_te

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

Even though readOnlyHint=true is already supplied, the description adds substantial behavioral context: validation evidence tiers, failure modes such as crossing quantiles or unstable tails, and concrete remedies like rearrangement/monotonization and avoiding sparse extreme quantiles. It also states a typical minimum N of 500, which is useful operational guidance an agent would not otherwise know.

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 dense but well-structured with clear labeled sections: Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, and Typical minimum N. The most important sentence is front-loaded. It is longer than minimal, but the added content is substantive and relevant rather than filler.

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-estimation tool, the description covers assumptions, prerequisites, failure modes, alternatives, and sample-size expectations. The main missing piece is guidance on choosing among the schema's method variants (ipw, dr, cic) and reconciling the description's mention of IV variants with a schema that does not expose an instrument parameter or an IV method option.

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 carries most parameter documentation. The description contributes domain-level context like 'avoid extreme quantiles where data are sparse' and the need for enough data across quantiles, but it does not provide specific parameter-by-parameter guidance beyond what the schema already says.

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 opening sentence states a specific verb and resource: 'Estimate distributional treatment effects.' It also lists alternatives (sp.qte, sp.iv, sp.dml), which helps an agent separate it from related tools. However, it does not explicitly explain how distributional_te differs from close siblings like qte or distributional_did.

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 clear context through assumptions (selection-on-observables, IV validity, rank invariance) and preconditions (covariates, treatment, outcome, enough data), so an agent can infer when the tool is appropriate. It names alternatives but does not spell out the conditional logic for when to choose one over another, stopping short of a full 5.

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