rdhte

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

Beyond the readOnlyHint annotation, the description discloses key behavioral and validity conditions: continuity of conditional expectations, no sorting around the cutoff, monotonicity for fuzzy designs, and bandwidth-sensitivity failure modes. It also warns about manipulation tests and recommends data-driven bandwidth selection, giving the agent realistic expectations about output reliability.

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 organized into clear labelled sections: assumptions, preconditions, failure modes, alternatives, and minimum sample size. Every sentence adds useful guidance, and the core purpose is front-loaded.

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 tool with 19 parameters and an output schema, the description is unusually complete: it states assumptions, data requirements, common failure modes, remedial actions, alternatives, and sample-size guidance. An agent has enough context to invoke this tool and to interpret potential warnings without additional lookups.

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?

The input schema covers 100% of parameters, so the baseline is 3. The description adds context about local polynomials, MSE-optimal bandwidth, and cutoff assumptions, but it does not describe individual parameters in greater depth than the schema already does.

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 verb and resource: 'Estimate conditional average treatment effects (CATE) in RD designs.' It clearly identifies the target estimand and design, and the mention of running-variable cutoff, local polynomial, and CATE distinguishes it from sibling RD tools that focus on ATE, bandwidth selection, or randomization inference.

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 explicit preconditions ('continuous running/forcing variable with a known cutoff', 'enough observations'), clear failure-mode warnings ('if manipulation is present the design is invalid'), and named alternatives (sp.rdrobust, sp.rdrandinf, sp.rdbwselect). It also gives a typical minimum N, so an agent can decide whether this tool is appropriate before invoking it.

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