iv_bounds

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

Annotations declare readOnlyHint=true, so the safety profile is already known. The description adds meaningful behavioral context beyond that: it states the result is an interval rather than a point, explains that only weak set-identifying assumptions are imposed, and describes failure modes (bounds too wide) with a remedy. It also notes the typical minimum N of 100. This goes beyond what annotations provide.

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 compact and information-dense, with clear labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). It front-loads the core purpose. The only minor inefficiency is that the failure-mode sentence is slightly run-on, but overall every sentence earns its place.

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?

Given the tool's complexity (14 params, output schema present, many siblings), the description covers the key decision-relevant context: what the tool computes, when to use it, what pre-conditions are needed, and how to respond to uninformative bounds. The output schema handles return-value details. It doesn't explain the 'less_than_late' assumption in depth, but the schema's enum description covers that.

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 the schema already documents all 14 parameters. The description adds some context for the 'assumption' parameter by explaining the two options ('monotone_iv' vs 'less_than_late') and their relative tightness, which is genuinely useful. However, it doesn't add meaning for most other parameters, so the 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 opens with a specific verb+resource: 'Nevo-Rosen (2012) bounds for LATE under imperfect instruments.' It clearly distinguishes this from point-identifying IV methods and names sibling alternatives (sp.oster_delta, sp.lee_bounds, sp.manski_bounds). The scope is precise: set-identifying bounds, not a point estimate.

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 explicit pre-conditions ('data needed for the point-identifying analysis, plus the weakest credible identifying restriction'), a specific condition for Lee bounds (binary selection/attrition indicator), and a failure-mode remedy ('Add a credible auxiliary restriction... to tighten the bounds'). It also names alternatives, giving an agent clear routing guidance.

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