rdbwhte

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds the optimization criterion ('MSE-optimal'), which is mild useful context, but does not disclose return structure, whether a model is fitted, or computational cost. No contradiction with annotations; it simply adds little beyond them.

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 a single nine-word sentence with zero fluff and the core object ('fully interacted RD model') front-loaded. However, it is terse to the point of under-specification: for a tool with 12 parameters and multiple bandwidth-selection siblings, the description omits the guidance the agent most needs, so brevity comes at the cost of usefulness.

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 rich schema (100% coverage, the `detail` enum with token estimates, output schema) and readOnly annotation carry much of the explanatory burden, so the description need not cover parameters or return values. The critical gap is situational: nothing tells the agent how this differs from rdbwselect/rdwinselect or in what analysis pipeline it belongs, which matters given the large sibling set.

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%, with all 12 parameters documented, so the schema carries the semantic burden and the baseline of 3 applies. The description does not add beyond the schema — though the phrase 'fully interacted' implicitly maps to the z parameter ('Covariate(s) for treatment effect heterogeneity'), the description never draws this connection.

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 states a specific operation (MSE-optimal bandwidth selection) and a specific resource (the fully interacted RD model). It partially distinguishes the tool from siblings like rdbwselect and rdwinselect by naming the 'fully interacted' model as the target, but leaves the term 'fully interacted' unexplained, which a less specialized agent may find cryptic.

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?

No guidance is given on when to use this tool versus rdbwselect, rdwinselect, rdbwsensitivity, or rd2d_bw, all of which are siblings in the bandwidth-selection space. The description implies usage via the word 'fully interacted' and the z parameter ('Covariate(s) for treatment effect heterogeneity'), but never explicitly states the selection condition or names an alternative.

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