Skip to main content
Glama
devbux

typesafe-mcp

by devbux
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Jev: box question (find where something is in an image)

jev_box

Locate one target in an image and return its bounding box edges as fractions of image size plus a confidence value. Pass the image in assets and name the target in instructions.

Instructions

Ask Jev a single Box question: locate one target in an image. Returns the box edges as fractions of the image size (top, bottom, left, right, each 0..1) plus a confidence value, under the question name "answer". The image must be in the request: reference it from the state or the instructions and pass it in assets. Box needs Jev 1.14, so this tool sends jev-1.14.0 unless you pass another model (jev-preview also works). A Box answer is always a box, even when the target is absent; pair it with jev_noul when you need a presence check.

Input Schema

NameRequiredDescriptionDefault
modelNoOptional Jev model id override (default: jev-1.14.0, because Box requires Jev 1.14).
stateYesThe situation: text, a JSON object, or a JSON array. Reference the image here (or in the instructions) where it belongs.
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.
instructionsYesWhat to find, and in which image: e.g. "the coffee mug in `photo`".
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. Changed4 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"
+}
    • 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

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the always-returns-a-box behavior, the required model version and default override, the image-in-request requirement, and the answer key/return shape. It omits any mention of permissions, latency, or failure modes when the image is missing.

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?

The core capability and return format are front-loaded in the first two sentences, with the model-default caveat and the jev_noul pairing placed after. It is a touch dense with parentheticals but every sentence carries actionable information.

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 5-param, nested-object tool with no output schema, the description supplies the missing return-value detail (top/bottom/left/right as 0..1 fractions, confidence, under "answer"), the image-in-request requirement, and the model-version constraint. Nothing an agent needs to call it correctly is absent.

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, but the description adds value beyond the schema by explaining *why* model defaults to jev-1.14.0 ("Box needs Jev 1.14") and by clarifying that the image is referenced from state/instructions and passed via assets. That reasoning is not derivable from the schema alone.

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 states a specific verb and resource — "locate one target in an image" and return box edges — and distinguishes the tool from the sibling `jev_noul` by framing Box as a localization tool versus a presence check. An agent can tell it apart from `jev_decide`/`jev_score`/`jev_noul` without opening any schema.

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 an explicit selection rule: "pair it with jev_noul when you need a presence check," plus the caveat that a Box answer is always a box even when the target is absent. It doesn't explicitly contrast with jev_decide/jev_choice/jev_score, so the routing across the full sibling set is incomplete.

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