Skip to main content
Glama

obsbot_tail2_track_target

Engage AI subject tracking at a normalized frame coordinate by passing x/y from a snapshot pixel divided by frame dimensions; verify ai_mode afterward because the tracking mode depends on the subject.

Instructions

Tap-to-track: give a normalized frame coordinate (x/y 0.01-0.99, top-left ~0,0) and the camera engages AI tracking on the subject there — measured to arm humanTrackingSingleMode on its own from mode none. Divide a snapshot pixel by frameWidth/frameHeight and pass it straight in. The mode that engages depends on what is at the point, so read it back (obsbot_tail2_status ai_mode) when it matters; objectTracking cannot be entered this way (it demands a bounding box the API grammar for which is not yet decoded).

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": {
      "x": "<x>",
      "y": "<y>"
    },
    "name": "obsbot_tail2_track_target"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYes
yYes
cameraNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.9.6
    • removedInput schema / properties / x / allOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "maximum": 0.99,
      -    "minimum": 0.01,
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / x / maximum
      Added value: +0.99
    • addedInput schema / properties / x / minimum
      Added value: +0.01
    • addedInput schema / properties / x / type
      Added value: +"number"
    • removedInput schema / properties / y / allOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "maximum": 0.99,
      -    "minimum": 0.01,
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / y / maximum
      Added value: +0.99
    • addedInput schema / properties / y / minimum
      Added value: +0.01
    • addedInput schema / properties / y / type
      Added value: +"number"
  2. Addedv0.9.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations the description carries the full burden, and it does substantial work: it discloses that the target mode is chosen from what is under the point, that it can start from mode none, and that you should read the resulting mode back via obsbot_tail2_status. It omits how tracking is stopped or reverted and whether the call fails when nothing trackable is at the point.

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 sentences, front-loaded with the action and coordinate convention, then the caveat. Minor waste in the awkward phrase "measured to arm humanTrackingSingleMode on its own from mode none," but almost every clause adds usable information.

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 3-parameter, no-annotation, no-output-schema tool this covers the core needs: what the call does, the coordinate convention, the mode-dependence caveat, and the readback step. Remaining gaps are the undocumented "camera" parameter and no mention of what the call itself returns.

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 0%, so the description must compensate, and it does for x/y: normalized 0.01-0.99 range, top-left ~(0,0) origin, and the pixel-to-normalized conversion recipe. The optional "camera" string parameter is never explained, so an agent has no guidance on which device identifier to supply when multiple cameras exist.

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?

"Tap-to-track: give a normalized frame coordinate ... and the camera engages AI tracking on the subject there" names a concrete verb and resource, and the note that objectTracking cannot be entered this way separates it from the bounding-box tracking path. It never names which sibling (e.g. track_custom or zone_tracking) covers the excluded case, so differentiation is partially implicit.

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 states the condition for use (you have a frame point of a subject), tells the agent how to produce that point (divide a snapshot pixel by frameWidth/frameHeight), and gives the exclusion that objectTracking cannot be reached this way. It also routes the agent to obsbot_tail2_status for verification; the only gap is that no alternative tool is named for the bounding-box tracking case.

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