rd_honest

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

Beyond the readOnlyHint annotation, the description discloses assumptions (bounded second derivative, continuity, no manipulation), preconditions (continuous x, sample mass on both sides), and failure modes with concrete remedies. It also exposes the key M tradeoff between tighter CIs and coverage risk. Nothing contradicts 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 long but information-dense: assumptions, preconditions, failure modes, and alternatives all earn their place. It is front-loaded with the core purpose. However, it is a single dense block rather than cleanly sectioned, and it ends abruptly with a truncated phrase ('or partia...'), which slightly hurts structural polish.

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 method with 15 parameters, the description covers selection-relevant context: statistical assumptions, data preconditions, parameter tradeoffs, alternative procedures, and failure-mode handling. Since an output schema exists, the description does not need to explain return values. An agent has enough to decide whether and how to invoke rd_honest.

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 baseline is 3. The description adds useful meaning for M — smaller M gives tighter CIs but riskier coverage — and references M_grid for sensitivity analysis. However, it adds little beyond the schema for the other 14 parameters, and the schema already documents them 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 identifies the tool as producing Armstrong-Kolesar (2018) honest confidence intervals for sharp regression discontinuity, which is a specific verb-resource pairing. It also distinguishes itself from rdrobust by emphasizing provable finite-sample coverage without bandwidth-selection bias, so an agent can tell it apart from the many RD sibling tools.

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 when-to-use and when-not-to-use guidance: run sp.mccrary_test alongside, pass an explicit M when the data-driven estimate is unreliable, prefer donut-hole RD if the McCrary test rejects, and report rd_honest together with rdrobust. It names rdrobust as the precision-oriented alternative and explains the tradeoff.

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