rifreg

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

The annotations already provide readOnlyHint=true, so the description carries a lower burden, but it still adds no behavioral context: nothing about fitting state, caching with as_handle, output payload, or what 'certified parity evidence' actually guarantees. It does not contradict the annotations, but it also does not enrich 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 definition is short, but the brevity comes from omission rather than disciplined conciseness. The first clause is tautological, and the second sentence about validation does not earn its place because its relevance is unclear.

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?

Even though the schema and output schema fill in many details, the tool description still fails to explain the method family, when to choose it, or how it relates to close siblings. For a 10-parameter estimator in a large sibling set, a one-line label plus a cryptic validation note is not enough.

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%, and every parameter already has a rich explanation, including defaults, enum meanings, and payload depth. The description itself adds no parameter-level meaning, so the schema carries the burden and 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 description essentially expands the tool name: 'RIF regression' restates 'rifreg' and adds a citation, but no main verb or outcome (e.g., 'estimates', 'computes unconditional quantile partial effects'). It also does not distinguish this from sibling tools like rif_decomposition or qreg.

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?

There is no guidance on when to use rifreg versus alternatives, nor any indication of when to set statistic='quantile' vs 'variance' vs 'gini'. The phrase 'Validation: certified parity evidence' reads as certification boilerplate, not usage direction.

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