Fetch a scenario's held-out input points as a fillable prediction skeleton. Fill y_pred (and optional y_std) without changing x, then call verify_prediction to check results.
Fetch a scenario's held-out INPUT points as a fillable skeleton. Fill y_pred (optionally y_std = your 1-sigma) and keep x unchanged, then call verify_prediction.
| Name | Required | Description | Default |
|---|---|---|---|
| scenario_key | Yes |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the return shape (a fillable skeleton with x, y_pred, y_std) and the constraint to leave x unchanged, but says nothing about read-only behavior, error cases, auth, or rate limits.
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 tight sentences with no waste, and the core action and the downstream workflow step are front-loaded. 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?
No output schema exists, so the description must explain the return value; it does so reasonably by describing the skeleton's fields and the required edit pattern. It is nearly complete for a one-parameter fetch tool, missing only edge-case or failure behavior.
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?
There is a single input parameter (scenario_key) with 0% schema description coverage. The description implies it selects 'a scenario' but adds no format, source, or validity details beyond that, so it only partially compensates for the schema gap.
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 (Fetch) and resource (a scenario's held-out INPUT points as a fillable skeleton), and identifies the follow-up tool verify_prediction so the agent understands its role in the workflow. It does not explicitly contrast with siblings like list_scenarios, but the resource is precise.
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 clear procedural guidance: fill y_pred (and optionally y_std), keep x unchanged, then call verify_prediction. This tells the agent when and how to use the tool relative to a named sibling. No explicit when-not conditions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.