suggest_dtypes

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

Details specific behaviors: proposing numeric conversions, category for low-cardinality, downcasting, and reporting savings. Covers key expectations.

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?

Three succinct sentences with no redundancy. Front-loaded with purpose, then behavior, then usage.

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?

Covers purpose, usage, and behavior well for a simple tool. Minor gap: no parameter explanations, but overall adequate.

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?

With 0% schema coverage, description should parameter details. It does not explain 'path' or 'max_rows', leaving their roles ambiguous.

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 recommends memory-efficient or correct column dtypes, distinguishing it from sibling tools that handle stats, quality, or profiling.

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?

Provides explicit use cases: shrink memory footprint or fix wrong types. No exclusions or alternatives mentioned, but context is clear.

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