compare_sources

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

No annotations are provided, so the description carries the burden. It discloses important behaviors such as auto-sampling sources over 500K rows, returning a verdict, and the specific statistical tests used. It does not explicitly mention read-only behavior or side effects, but the analysis nature is implied.

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 compact and informative, with each sentence delivering a distinct fact: purpose, verdict, numeric methods, categorical methods, auto-sampling, and optional parameter. No wasted words.

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 moderately complex analysis tool, the description covers the core behaviors: the comparison scope, statistical tests, sampling strategy, and optional key-based overlap. With an output schema present, the lack of return-value details is acceptable. It could be more explicit about prerequisites or when to use alternatives, but overall it is sufficient.

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?

The schema has no parameter descriptions, but the description explains that source_a and source_b are the two sources being compared and that `keys` enables join-key overlap stats. This adds meaning beyond the bare 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 performs schema diff and per-column distribution drift between two loaded sources, with specific outputs (drop-in verdict) and statistical methods (PSI, KS, chi-square). This distinguishes it from sibling tools like check_distributions (single source) and auto_compare.

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 implies usage for comparing two already-loaded sources and advises passing `keys` for join-key overlap stats. However, it does not explicitly state when to prefer this over alternatives like auto_compare or compare_groups, nor give exclusions.

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