rd_distribution

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

Annotations already mark the tool as read-only, so the description's job is to add context beyond safety. It adds statistical assumptions, manipulation checks, bandwidth-sensitivity guidance, and follow-up alternatives, all of which go well beyond the annotations. There is no contradiction with readOnlyHint.

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?

Longer than average, but it is organized into labeled sections (assumptions, preconditions, failure modes, alternatives, minimum N) and nearly every sentence carries useful information. The opening phrase is terse and front-loaded, with no filler or tautology.

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?

Given the tool's complexity and the presence of an output schema, the description covers the key statistical context: assumptions, validity preconditions, failure modes, remediation paths, and a sample-size threshold. The main omission is a plain-language statement of what the distribution-valued estimate actually represents and how it should be interpreted.

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 a baseline of 3 is appropriate even though the description itself says little about parameter formats. It does reinforce the meaning of cutoff and running variable and the importance of sample size near the cutoff, but it adds no concrete parameter-format guidance beyond the schema.

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 identifies a specific resource—a sharp regression-discontinuity design—and a distinguishing scope ('distribution-valued') that separates it from average-effect RD tools like rdrobust. However, it is phrased as a noun phrase rather than an explicit verb statement of what the tool computes, and 'distribution-valued' is not unpacked.

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 explicit preconditions, assumptions, failure modes, and a typical minimum N, plus named alternatives for follow-up actions such as density tests, donut-hole RD, or bounds. It stops short of directly saying 'use rdrobust for average effects, use this for distributional effects,' so the choice among the listed alternatives is mostly implicit.

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