General Decision MCP

jev_rank

Read-only

Rank bounded candidates by native Choice probabilities, preserve dependencies, and surface probability-order violations for advisory decision support only.

Instructions

Rank bounded candidates by native Choice probabilities, preserving dependencies and surfacing any probability-order violations. Advisory only; never grants authorization or executes actions.

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": {
      "task": "<task>",
      "priorities": "<priorities>",
      "evidence": "<evidence>",
      "candidates": "<candidates>"
    },
    "name": "jev_rank"
  }
}

Input Schema

Name	Required	Description
`task`	Yes
`scope`	No	Known consequence scope; omitted means unknown and requires human review.
`evidence`	Yes	Supplied text only; no files or URLs are fetched.
`candidates`	Yes
`priorities`	Yes
`evidence_complete`	No	Caller attests supplied evidence is complete; omitted means incomplete. Not independent verification.

Output Schema

Name	Required	Description	Default
`tool`	Yes
`error`	No
`model`	Yes
`usage`	Yes
`policy`	Yes
`status`	Yes
`answers`	Yes
`summary`	Yes
`evidence`	Yes
`provider`	Yes
`schema_version`	Yes
`requested_model`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnly/destructive=false, so the advisory framing is partly redundant, though it usefully confirms no authorization is granted. It does not disclose that idempotentHint=false means repeated calls may yield different orderings, nor what happens when probability-order violations are detected (error vs. annotation in results).

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?

Two tight sentences, front-loaded with the core verb and resource; the constraint clause follows. No filler and nothing repeated verbatim from the annotations or schema.

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?

Output schema exists so return values needn't be explained, but for a 6-parameter, 4-required ranking tool the description leaves meaningful gaps: non-determinism, violation handling, and the evidence_complete/scope review implications are absent. Adequate as a minimum-viable definition, not more.

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?

At 50% schema coverage, the description only hints at 'candidates' and 'dependencies' (maps to candidates/depends_on) and 'bounded' (tied to maxItems). It says nothing about priorities, evidence, evidence_complete, or the human-review consequence of omitting scope, leaving the undocumented half uncovered in both description and schema.

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?

States a specific verb and resource: 'Rank bounded candidates by native Choice probabilities,' plus two behavioral facets (dependency preservation, probability-order violation surfacing). It never differentiates itself from plausible siblings like jev_decide, jev_risk, or jev_screen, so an agent cannot tell from the text alone when ranking beats deciding.

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

Usage Guidelines3/5

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

'Advisory only; never grants authorization or executes actions' establishes a clear when-not boundary and prevents misuse as a gate. However, there is no positive guidance on when to call this versus a decision or risk tool, and no mention of prerequisites such as complete evidence or a declared scope.

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

Deploy Server