rdms

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the tool is a read-only estimator. The description does not contradict this. It goes well beyond annotations by explaining assumptions (continuity, no manipulation, monotonicity for fuzzy), failure modes (manipulation, bandwidth sensitivity), and validation ('certified parity evidence'). This is rich behavioral context for an agent deciding to call it.

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?

Although the description is long, it is tightly organized with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Every sentence carries unique information; there is no fluff. For a complex econometric method with many statistical requirements, this density is appropriate and efficient.

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?

The description covers purpose, assumptions, pre-conditions, failure modes, alternatives, and sample-size guidance. With an output schema present and annotations declaring read-only behavior, nothing essential is missing. Even the handling of failure modes (run a McCrary test, use MSE-optimal bandwidth) is specified, making this a fully self-contained tool definition.

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 context about running variables being geographic distances and mentions bandwidth, but does not provide additional parameter-specific semantics beyond what the JSON schema already documents. It does not, for example, explain the distinction between bandwidth and cutoff2 or the meaning of alpha beyond the schema. Thus the description adds modest value but not enough to raise the score.

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 'Multi-score / Geographic RD design at a single boundary point', a specific verb+resource that clearly distinguishes it from single-score RD tools (rdrobust, rdd) and multi-cutoff variants (multi_cutoff_rd). It further clarifies the two running variables (x1, x2) are geographic distances to the boundary, so an agent can immediately tell what this tool does and how it differs from siblings.

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 explicitly lists assumptions, pre-conditions, failure modes, and alternatives (sp.rdrobust, sp.rdrandinf, sp.rdbwselect). It even provides a typical minimum N of 500. An agent knows exactly when to use this tool (multi-score/geo RD with valid continuity and no sorting) and when to switch to a different tool. No ambiguity remains.

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