Fit a versioned local output calibrator for audience-response cues using train/validation splits and a held-out test, without adopting or overwriting any existing model.
Fit a versioned local output calibrator using train/validation; test is held out. Does not adopt or overwrite any model.
| Name | Required | Description | Default |
|---|---|---|---|
| dataset | Yes | ||
| options | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, non-open-world. The description adds genuinely new behavioral context: the calibrator is versioned, local, built from train/validation with test held out, and it explicitly does not adopt or overwrite any model. It stops short of saying how/where the fitted calibrator is returned or stored.
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 tightly written sentences, front-loaded with the core action and followed by the key held-out/adoption constraint. Zero filler and every clause carries information.
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 complex training tool with nested free-form objects, 0% schema description coverage, and no output schema, the description is thin: it never explains the dataset/options shape or what fitting returns. It covers the essential intent but is inadequate for correct invocation.
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 0% and both parameters (dataset, options) are untyped free-form objects with additionalProperties true. The description implies 'dataset' carries the train/validation/test splits but adds no structure for dataset or options, leaving the agent to guess the input contract.
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+resource: 'Fit a versioned local output calibrator' using train/validation. This implicitly distinguishes it from the sibling ap_apply_calibration (fit vs apply), but it never names or contrasts a sibling explicitly. Clear enough for an agent to know it trains/creates a calibrator rather than applying one.
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?
Usage is only implied: the train/validation/test split hints at a training step, and 'Does not adopt or overwrite any model' clarifies scope, but there is no explicit when-to-use, prerequisites, or routing against ap_apply_calibration/ap_tune_parameters. The agent must infer the workflow position.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.