kan_dlate

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

Annotations only cover read-only and closed-world hints. The description adds deprecation status, detailed assumptions, pre-conditions, failure modes (non-monotone quantiles, unstable tails) with remedies, and minimum sample size. This is rich behavioral context far beyond what annotations provide, with no contradiction.

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 organized with clear labels (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) and opens with the deprecation notice. Each segment carries useful content, though the block is dense and technical, making it slightly harder to scan quickly for an agent.

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 full schema (100% parameter coverage), an output schema, and annotations, the description supplies all decision-relevant context: deprecation, assumptions, preconditions, failure modes with workarounds, alternatives, and minimum sample size. An agent has enough information to select the tool, avoid it, or take corrective action based on failure modes.

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%, so the schema already describes all 14 parameters. The description mentions covariates, treatment, outcome, and instrument in the pre-conditions, and alludes to quantiles in the failure-mode section, adding slight context. But it does not clarify the cryptic `quantiles` schema description or add parameter-specific semantics, so 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?

Description explicitly identifies the tool as a deprecated alias for :func:`dist_iv`, naming the specific resource it delegates to and distinguishing it from siblings. However, it never states the underlying action of dist_iv (i.e., what is actually estimated), relying on the alias target and technical assumptions (IV-QTE, quantiles) to convey the purpose. This is clear but not fully self-contained.

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 when-not-to-use guidance by labeling the tool 'deprecated' and listing alternatives: sp.qte, sp.iv, sp.dml. It also provides preconditions, assumptions, and typical minimum N, letting an agent decide whether this tool is appropriate or whether to use a non-deprecated sibling.

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