copula_sensitivity

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

Annotations declare readOnlyHint=true, so the agent knows this is a read-only analysis. The description adds the Gaussian-copula modeling assumption, which is useful behavioral context beyond the annotation. However, it does not disclose what the output contains (e.g., bias-adjusted estimates, confidence intervals, plots) or whether it returns a fitted object, despite the output schema existing. No contradiction with annotations.

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, compact sentence that conveys the core method and target. It is front-loaded and free of fluff. It could add a bit more context without becoming verbose, but as written it is appropriately concise.

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 has 12 parameters, a rich schema, and an output schema, the description is minimally adequate but leaves gaps. It does not explain what the tool returns, how to interpret the sensitivity results, or when to choose it over the many sibling sensitivity tools. The schema covers parameters, but the description does not help an agent decide whether this is the right tool for a given confounding problem.

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 12 parameters. The description adds no parameter-level meaning beyond the schema. The schema itself provides rich detail (e.g., 'detail' levels, sigma_u/sigma_y percentile scaling, as_handle caching), 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 'Gaussian-copula sensitivity to unobserved confounding' identifies a specific statistical method (Gaussian copula) and its purpose (sensitivity analysis for unobserved confounding). It is clear enough to distinguish from generic 'sensitivity' tools, though it does not explicitly name sibling alternatives or state what the tool produces (e.g., a sensitivity table, plot, or bounds).

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 alternatives like 'sensitivity', 'sensemakr', 'evalue', 'unified_sensitivity', or 'synth_sensitivity'. It does not state prerequisites (e.g., needing a fitted model, estimate, and standard error) or what kind of confounding scenario it addresses. The agent must infer usage from the name and parameters.

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