rd_lasso

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

Annotations declare readOnlyHint=true and the description does not contradict this. It adds valuable behavioral context beyond the annotation by listing validity assumptions and failure modes—manipulation/sorting and bandwidth sensitivity—which directly affect how results should be interpreted. It could go further by describing the exact return payload, but the output schema covers that.

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 dense but well organized into labeled blocks: assumptions, pre-conditions, failure modes, alternatives, and minimum N. Every section earns its place and the most identifying phrase is front-loaded. An agent can scan it quickly and extract the needed guidance without wading through filler.

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 14-parameter causal-inference tool, the description covers the essential selection and invocation context: assumptions, preconditions, failure modes, remedies, alternatives, and sample-size guidance. Combined with the complete input schema and the presence of an output schema, an agent has enough to decide when to call it and what to expect.

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 all 14 parameters are already documented in the input schema. The description adds some contextual framing, such as data-driven MSE-optimal bandwidth and candidate covariates for post-double-selection, but it does not systematically enrich individual parameter meanings. Baseline 3 is appropriate.

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 opening phrase specifies exactly what the tool does—LASSO-assisted RD via post-double-selection—and distinguishes it from siblings like rdrobust and rdrandinf by naming the LASSO machinery. The alternatives list reinforces differentiation. Although it lacks a direct verb, the method label is precise and domain-appropriate.

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 pre-conditions (continuous running variable, known cutoff, enough observations) and assumptions, plus a typical minimum N. Failure modes tell the agent when the design is invalid and what to do, and alternatives are named. However, it does not give a crisp decision rule for when to choose rd_lasso over rdrobust or rdrandinf.

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