oddsky

check_prediction

Grades a registered prediction against current case data, marking predictions with open windows as pending and skipping writes on dry runs.

Instructions

Grade a registered prediction against the data now in the case. Predictions whose window has not closed yet are reported as pending and not graded. dry_run=True never writes. (Not available in blind trials, where the future is held back.)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "case": "<case>",
      "prediction": "<prediction>"
    },
    "name": "check_prediction"
  }
}

Input Schema

Name	Required	Description	Default
`case`	Yes
`dry_run`	No
`prediction`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Nov 12, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description does real work: it discloses the pending/not-graded rule, says dry_run=True never writes (implying the default does write), and names the blind-trial restriction. It still leaves open what exactly is written on a real run, whether a prior grade is overwritten, and whether grading is idempotent or reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core action, then the pending rule, then the write/availability caveats. Nothing is redundant and no sentence could be dropped without losing a constraint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter grading tool with no annotations and no output schema, the description covers dry_run, pending behavior, and trial restrictions, but says nothing about the shape of the grading result (correct/incorrect/score), which matters because no output schema exists. It is adequate but leaves the agent guessing at the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry all parameter meaning, and it only fully explains dry_run. "case" and "prediction" are identifiable by name and by "registered prediction," but no identifier format or lookup convention is given, leaving partial compensation for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and object: "Grade a registered prediction against the data now in the case." That distinguishes it cleanly from the sibling register_prediction, since one creates a prediction and this one evaluates an existing one, and it states the evaluation basis (current case data).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete conditions: predictions with an open window are returned as pending rather than graded, dry_run=True is the no-write path, and the tool is unavailable in blind trials. That is strong context, but it never states who should call it or what to do instead when blocked (e.g., in blind trials or for a pending prediction), so it falls short of explicit alternative routing.

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