Compare real and synthetic datasets by calculating their marginal distribution score, where a lower score indicates more similar distributions.
Calculate marginal distribution score between two datasets (real vs synthetic). Lower score means more similar distributions.
| Name | Required | Description | Default |
|---|---|---|---|
| dataset_ids | Yes | Exactly 2 dataset IDs: [real_dataset_id, synthetic_dataset_id] |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It usefully discloses the metric's semantics (lower score = more similar distributions), but says nothing about whether the call is read-only, how expensive the computation is, or whether it requires a completed training/generation job to exist first. Adequate but with real gaps.
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?
Two short sentences with no filler. The core action is front-loaded and the interpretation of the result follows immediately, so every sentence 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?
For a single-parameter compute tool with no output schema, the description supplies the one thing an agent actually needs about the return value: the direction of the metric. It stops short of stating the score's range/scale or the cost of the computation, but it is close to complete for this level of complexity.
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% and the single parameter is fully documented in the schema, including the required ordering [real_dataset_id, synthetic_dataset_id]. The description adds no ordering or format detail beyond that, so the baseline of 3 applies.
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?
States a specific verb (calculate) and resource (marginal distribution score) plus the operand (two datasets, real vs synthetic). The meaning of the output is also stated, which lets an agent understand the result without opening a schema. It does not, however, distinguish itself from the nearby plot_distribution sibling, which is also a distribution-comparison tool.
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?
No when-to-use, prerequisites, or exclusions are given. The sibling plot_distribution is a plausible alternative for comparing real vs synthetic distributions, and the description never says when to pick this score over that plot. Usage must be inferred entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.