openjev-mcp

Jev score

jev_score

Read-onlyIdempotent

Ask one question to score content on an ordered scale you define, returning a probability-weighted score, distribution, and confidence for degree, severity, or intensity.

Instructions

Ask one question whose answer is a position on an ordered scale you define.

Use for degree, severity, or intensity. criteria lists the levels from lowest to highest; a three-level scale returns a score from 0 to 2, and values between integers are positions between levels — the score is the probability-weighted mean of level numbers, not a percentage or a category id. Give every level a self-contained description ("no deadline expressed", "wants a response soon", "explicit deadline"), never a relative one like "more urgent than the level below".

Returns the score, the legend mapping level numbers to their descriptions, the full distribution, and confidence. Two different distributions can produce the same score, so read probabilities when the difference matters — all weight on level 1 and an even split between 0 and 2 both average to 1.

Input 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. The state is judged as one whole, so an array of tickets gets one blended answer rather than one per ticket; to judge records one by one, use `jev_batch`. 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 ordered levels, lowest first. Each level is a self-contained description (a string, or an object/array holding meaning and examples). A three-level scale returns a score from 0 to 2; fractional scores fall between levels, so each level must stand on its own rather than say "same as the level below".
`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

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.

Changed1 schema field changedv0.2.0Oct 14, 2026

changedInput schema / properties / state / description

Previous value: -"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."New value: +"The content the questions are judged against: text, an object of named fields, or an array of records. The state is judged as one whole, so an array of tickets gets one blended answer rather than one per ticket; to judge records one by one, use `jev_batch`. 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."

First observedv0.1.1Sep 22, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial non-obvious semantics: the score is a probability-weighted mean, not a percentage or category id; fractional scores are interpolations between levels; and two distributions can yield the same score, so probabilities must be read when the difference matters. That is real behavioral context an agent cannot get from the schema.

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

Conciseness4/5

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

Front-loaded with the core action, then scale semantics, then return-value caveats. Every paragraph earns its place, though the closing distribution example is slightly verbose for the value it adds.

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

Completeness5/5

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

For a judgment primitive with an output schema and full annotation coverage, the description fills the remaining gaps: how to construct criteria, what the numeric score means, and what else comes back. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: criteria must be ordered lowest-first, each level must be self-contained (with the reason — fractional scores fall between levels), and a three-level scale yields 0-2. These constraints materially affect correct invocation.

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

Purpose4/5

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

The first sentence gives a specific verb (ask) and the exact output shape (a position on an ordered scale the caller defines), which separates it cleanly from a categorical sibling like jev_choice. It does not name the sibling it is not, so differentiation is left to inference from the scale wording.

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?

"Use for degree, severity, or intensity" gives clear positive selection criteria, and the schema adds the routing rule to jev_batch for per-record judging. There is no explicit when-not-to-use statement or named alternative (e.g. jev_choice) in the description body.

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

Deploy Server