Skip to main content
Glama
devbux

typesafe-mcp

by devbux
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Jev: decide (multiple typed questions)

jev_decide

Ask the Jev decision model multiple typed questions—choices, scores, true/false, or image boxes—about a text or JSON state and get structured answers with calibrated probabilities in one call.

Instructions

Ask TypeSafe AI's Jev decision model one or more typed questions (choice, score, noul and/or box) about a state in a single call. Returns typed answers with calibrated probabilities. The state may be text or structured JSON. Images: pass them in assets and write each image's reference in the state, instructions, or criteria where it belongs.

Input Schema

NameRequiredDescriptionDefault
modelNoOptional Jev model id override (default: jev-latest).
stateYesThe situation to decide about: text, a JSON object, or a JSON array.
assetsNoImages keyed by reference string. Write each reference in the state, instructions, or criteria where the image belongs. PNG or JPEG only, base64-encoded with no data: prefix. API limits: 16 MiB per image, 280-1568 px per side.
questionsYesMap of question name to typed question. Each question has a type (choice | score | noul | box), instructions, and criteria: choice = object of option label -> description (string, structured object/array, or null; 2-255 options); score = array of at least 2 ordered level descriptions (strings or structured entries); noul = optional object of true/false descriptions; box = instructions only, no criteria (finds where something is in an image). Instructions may be text or structured JSON.
long_contextNoOpt into Jev's 262k long-context limits (an experimental danger-zone feature: slower and less accurate).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.2.3
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / assets / additionalProperties / additionalProperties
      Removed value: -false
    • addedInput schema / properties / assets / propertyNames
      Added value: +{
+  "type": "string"
+}
    • removedInput schema / properties / questions / additionalProperties / additionalProperties
      Removed value: -false
    • changedInput schema / properties / questions / additionalProperties / required
      Previous value: -[
-  "type"
-]New value: +[
+  "type",
+  "instructions"
+]
    • addedInput schema / properties / questions / propertyNames
      Added value: +{
+  "type": "string"
+}
    • changedInput schema / properties / state / anyOf
      Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "additionalProperties": {},
-    "type": "object"
-  },
-  {
-    "items": {},
-    "type": "array"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  {
+    "items": {},
+    "type": "array"
+  }
+]
  2. First observedv0.2.2

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description must carry behavioral disclosure; it does say the call returns typed answers with calibrated probabilities and accepts text or structured state, which is more than nothing. It says nothing about latency/cost, batching limits, determinism, or failure modes, and leaves long-context behavior to 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?

Three compact sentences, front-loaded with what the tool does and what it returns, then the image caveat. No filler, though the image sentence is somewhat dense and could be trimmed since the schema repeats it.

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 5-param nested tool with no output schema, the description covers purpose, accepted state formats, the four question types, and the general return shape (typed answers with calibrated probabilities). Missing detail on the answer payload structure and multi-question semantics is partly mitigated by the exhaustive schema text.

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 coverage is 100%, so the schema already documents all five parameters. The description's image note (pass in `assets` and reference each image in state/instructions/criteria) largely restates what the `assets` schema description says, adding little beyond the structured field. Baseline 3 applies.

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 (ask the Jev decision model typed questions) and enumerates the question types (choice, score, noul, box), which implicitly maps to the sibling tools. It signals batching ('one or more ... in a single call') without naming jev_choice/jev_score/etc. as alternatives, so differentiation is present but inferential.

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?

The phrase 'one or more typed questions ... in a single call' hints that this is the multi-question entry point, and the image guidance covers one specific case. But there is no explicit 'use this instead of jev_choice when...' routing or statement of when a single-type sibling is preferable.

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

Deploy Server

Other Tools