Skip to main content
Glama
Sign In
Tehnolabs

PixelForge MCP

by Tehnolabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Detect Objects

detect_objects

Identify objects in an image and return normalized bounding-box coordinates for each detected item.

Instructions

Detect objects in an image with bounding boxes.

Uses Gemini's zero-shot object detection. Returns bounding box coordinates normalized to 0-1000 scale as [y_min, x_min, y_max, x_max].

Input Schema

NameRequiredDescriptionDefault
modelNoAnalysis model override. Default gemini-3.5-flash-lite. Use gemini-3.8-flash for harder OCR or reasoning.
objectsNoSpecific objects to detect (e.g. "cats and dogs"). Default: detect all visible objects.
image_pathYesPath to the image
use_groundingNoEnable Google Search grounding for more accurate, factual results.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.0
    • addedInput schema / properties / model
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Analysis model override. Default gemini-3.5-flash-lite.\nUse gemini-3.8-flash for harder OCR or reasoning."
+}
  2. First observedv0.5.4

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 does carry the burden, and it usefully discloses the backend, the zero-shot nature (no example images needed), and the exact coordinate scale/order including the non-obvious [y_min, x_min, y_max, x_max] ordering. It says nothing about failure modes (non-image paths), cost, latency, or how many objects are returned, so the operational profile is incomplete.

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 short sentences, front-loaded with the action and followed by the two facts an agent most needs (mechanism and coordinate format). The coordinate-order detail partially overlaps the output schema but is dense enough to earn its place.

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?

With an output schema present, return values need not be re-explained, and all four params are fully covered by the schema. What remains missing is selection guidance relative to the other image tools; otherwise the definition is sufficient to invoke correctly.

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 description coverage is 100%, so all four parameters (image_path, objects, model, use_grounding) are already documented, including the model override guidance and the objects filter example. The description adds no parameter guidance beyond that, so the baseline of 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 ('detect objects in an image with bounding boxes') and adds the mechanism (Gemini zero-shot detection). It never names or contrasts with the closest sibling, analyze_image, so an agent must infer why it should pick this over a general image analysis call.

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?

Usage is only implied by the output format: wanting bounding boxes selects this tool. There is no explicit when-to-use, no when-not-to-use, and no reference to analyze_image, extract_text, or compare_images, all of which could plausibly be chosen instead.

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