dist_iv

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

Although annotations already mark the tool as read-only, the description adds substantial behavioral context: assumptions, relevance checks, over-identification testing, quantile-crossing failure modes, weak-IV remedies, typical minimum N, and validation evidence tiers. This goes well beyond what the annotations alone convey.

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 long but organized into labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) — every section earns its place for a complex estimator. It is somewhat dense, but it is structured well and front-loads the core estimand.

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 complex distributional IV-QTE tool with 15 parameters, 4 required fields, an output schema, and rich annotations, the description is remarkably complete. It covers validity conditions, failure modes, alternative methods, sample-size guidance, and failure remedies, leaving little an agent would need to infer on its own.

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 coverage is 100% and individual parameter descriptions already carry meaning (defaults, enum behavior, payload depth, caching semantics). The description adds some context, such as the parenthesized endog ~ instruments block and the relevance condition, but many parameter-level details are left to the schema. 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 precise estimand — "complier LATE at each quantile of y" — which identifies the method and its target. It names alternatives (sp.qte, sp.iv, sp.dml, sp.deepiv), helping an agent distinguish it from closely related IV and QTE tools.

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, assumptions (e.g., rank invariance, valid instrument, first-stage F >= 10), and failure-mode remedies, giving the agent clear context for when the tool applies. It names alternatives but does not explicitly state when to prefer one sibling over another, so it falls just short of full routing guidance.

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