openjev-mcp

Jev choice

jev_choice

Read-only

Select exactly one option from a predefined set based on input content, returning the chosen option, probability distribution, and confidence. Use for classification, routing, or single-choice decisions from a closed list.

Instructions

Ask one question whose answer is exactly one of a set of options you define.

Use for a category, a route, or a selection from a closed list — not for a degree and not for a yes/no. Write the judgment in instructions, and put the boundaries in the option descriptions: what each option covers and excludes. Include an option named "other" or "none" when the list may not cover every input. A choice returns exactly one option, so ask separate noul questions (together in jev_ask) when several labels can apply at once.

Returns the selected option, the full probability distribution, and confidence. Confidence summarises how concentrated the distribution is — it is not the probability that the selection is correct. Compare it against a threshold you calibrated on your own examples, and send anything below it to a person instead of acting on it.

Input Schema

TableJSON Schema

Name	Required	Description
`model`	No	Model alias. Omit to use the server default (`openjev`).
`state`	Yes	The content the questions are judged against: text, an object of named fields, or an array of records. Reference a nested field from `instructions` with a dotted path in backticks, e.g. `account.plan`. Fetch external records first — a URL here is not a request to browse — and note that this API accepts no image, audio, or file uploads.
`criteria`	Yes	The options. An object maps each option name to a description of what it covers and excludes; an array of names is shorthand for options that need no description. Include an option named "other" or "none" when the list may not cover every input.
`question_id`	No	Label for this question in the response. Defaults to the primitive name.
`instructions`	Yes	The judgment to make, written out in full. A clear specific string is usually enough; use an object or array when the judgment, its scope, and its constraints belong together. The question id is not sent to the model, so never rely on it to carry meaning.

Output Schema

TableJSON Schema

Name	Required	Description
`hints`	No	Non-blocking advice about this request, when there is any.
`model`	No
`usage`	No
`answer`	Yes
`question_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Sep 22, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description goes beyond by detailing the return value ('the selected option, the full probability distribution, and `confidence`') and crucially explains the semantics of `confidence`: it is 'not the probability that the selection is correct' but a measure of distribution concentration, with actionable advice to compare against a calibrated threshold and escalate low-confidence results to a human. This is rich behavioral context not present in annotations.

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?

The description is a single tight paragraph of about 150 words. It opens with the core purpose, then delivers usage rules, option structuring, and return/confidence handling in logical order. Every sentence earns its place—no redundancy or filler. It is front-loaded with the most critical info and remains skimmable.

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

Completeness4/5

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

For a tool with 5 parameters (3 required) and a complex judgment task, the description covers the essential aspects: how to define options with boundaries, when to include 'other'/'none', the instruction form, and how to interpret the output. It does leave out explicit error cases or edge conditions, but the output schema (present per context) likely fills that gap. Given the richness already present, the description is quite complete.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: for `criteria` it explains the object form (each option maps to a description of what it covers/excludes) and the array shorthand, plus the 'other'/'none' guidance; for `instructions` it says to write the judgment in full; for `state` it warns that a URL is not a browse request and clarifies no file uploads. These enrich the parameter understanding and compensate for the generic schema descriptions.

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 precise verb-resource-action: 'Ask one question whose answer is exactly one of a set of options you define.' It immediately scopes the tool to category/route/closed-list selection and explicitly excludes degree and yes/no uses, distinguishing it from siblings like jev_score and jev_noul. The statement is unambiguous and tied to a specific resource and constraint.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use guidance: 'Use for a category, a route, or a selection from a closed list — not for a degree and not for a yes/no.' It also names the sibling for multi-label cases: 'ask separate noul questions (together in `jev_ask`) when several labels can apply at once.' Additionally, it advises including 'other' or 'none' for open lists, aligning with the openWorldHint. This provides clear routing and alternatives.

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

Deploy Server