preflight

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds useful context about the kinds of checks performed and the verdict format, which goes beyond the annotation. It does not describe side effects (none expected) or any state changes, but that is consistent with the read-only hint.

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 two sentences with no fluff. The first sentence states the purpose and verdict, the second gives the usage rule and examples. It is front-loaded and every word 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?

The tool has an output schema, so return values are defined. The description covers when to use it and what it checks. Given the tool's complexity (15 parameters, many methods), the description does not explain how the method parameter maps to specific checks, but that may be covered by the output schema. Overall, it is adequate for an agent to know when to call it.

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 60%, meaning 9 of 15 parameters have descriptions; the remaining six (time, cohort, treatment, instrument, running_var, etc.) lack descriptions. The tool description does not add any parameter-specific guidance or compensate for these gaps. It only mentions 'DataFrame' generically, so it adds no semantic value beyond the schema.

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 clearly states the tool runs pre-fit identification checks on a DataFrame and returns a verdict. It names the specific design problems it surfaces (overlap, cohort sizes, IV first-stage F, running-variable density), which distinguishes it from fitting tools. However, it does not explicitly differentiate from the sibling 'check_identification', so it loses a point for not addressing that alternative.

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 an explicit when-to-use rule: 'ALWAYS call this before fitting on an unfamiliar dataset'. It also explains the benefit (surfacing design problems). It does not mention when not to use or name alternative tools like check_identification, so it is strong on when but lacks exclusionary guidance.

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