rdrbounds

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

The annotation readOnlyHint=true already indicates the tool is a safe read operationulating no side effects. The description adds no further behavioral context—such as that it performs permutation-based inference, returns a sensitivity table, or requires a pre-specified window. Since annotations carry the safety profile, the description's lack of additional behavior detail keeps this at a low but not contradictory level.

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, dense noun phrase with zero filler words. It conveys the core purpose in six words and earns its place. There is no structural waste or redundancy.

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 are rich, the description itself is too terse to orient an agent about when to choose this tool among the dozens of related sensitivity and RD tools. It does not explain what 'under local randomization' implies for inputs (e.g., the need for a window or running variable), nor does it reference typical workflows or alternatives. A more complete description would mention usage context and relationship to siblings.

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?

The schema describes all 15 parameters with 100% coverage, so the heavy lifting is done by the schema. The description itself adds no parameter-specific meaning, but per the baseline for high schema coverage, a score of 3 is appropriate. It does not mislead or omit information beyond what the schema already provides.

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 'Rosenbaum sensitivity bounds for RD under local randomization' clearly identifies the statistical method and the specific application domain (regression discontinuity under local randomization). It distinguishes from siblings like rosenbaum_bounds and rdwinselect by adding the 'under local randomization' qualifier. However, it lacks an explicit verb such as 'computes' or 'estimates', making it slightly less directive than a full action-resource statement.

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 provides no guidance on when to use this tool versus the many related siblings (e.g., rosenbaum_bounds, rosenbaum_gamma, rdwinselect). It does not state conditions, exclusions, or mention that it is appropriate only when working with RD designs under local randomization. An agent must infer usage solely from the name and schema, which is insufficient.

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