Skip to main content
Glama
rebot-mcp

rebot-mcp

Official

detect

Run one vision inference on a fresh frame to locate objects or ArUco markers, choosing YOLO, ArUco, or both, and return normalized bounding boxes.

Instructions

Run one detector inference on a fresh frame. Boxes are normalised [x0, y0, x1, y1] in the image (0..1). pipelines: yolo (objects), aruco (markers) or both (default); honoured by rebot-vision >= 1.3, older detectors run their current mode. The result's pipelines lists what ran (null when the detector does not report it).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "detect"
  }
}

Input Schema

NameRequiredDescriptionDefault
wait_msNo
min_scoreNo
pipelinesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does useful work by disclosing that a fresh frame is captured, that boxes are normalised, that the pipelines option is version-gated (honoured by rebot-vision >= 1.3, older detectors run their current mode), and that the result's pipelines field may be null. It says nothing about blocking/latency, what wait_ms waits for, or failure behaviour when no detector is available.

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?

Four short sentences, front-loaded with the core action and followed by output format and the pipelines caveat. Dense and largely waste-free; the version-compatibility sentence is long but earns its place.

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?

For a perception tool with no annotations, no output schema, and three undocumented parameters, the description covers the return shape (boxes format, pipelines field) but leaves timing, blocking behaviour, and two of three parameters unexplained. It is adequate but has clear gaps for a tool an agent must 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 0%, so the description must compensate, and it only partially does. It thoroughly explains 'pipelines' (yolo = objects, aruco = markers, both = default, plus version dependence), but 'min_score' and 'wait_ms' are never mentioned despite their 0..1 and 0..5000 ranges needing interpretation.

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 description states a specific verb and resource: run one detector inference on a fresh frame, and it clarifies the output geometry (normalised [x0, y0, x1, y1] boxes in 0..1). That is enough to distinguish it from snapshot/snapshot_annotated, which capture imagery rather than run inference, but no sibling is named explicitly.

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: the agent can infer this is the tool that produces detections on a newly captured frame. There is no statement of when to prefer it over snapshot_annotated, no prerequisite (e.g. control ownership, detector configuration), and no exclusion for cases where a stored snapshot should be reused.

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