Skip to main content
Glama
Sign In
Daz3D-MCP

Daz3D-MCP

by MictlanLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

camera_shot

Places and sizes a camera for film shots of a character’s face, keeps framing on one side of the eyeline for matching reverse shots, and reports heads blocking the view.

Instructions

Places a camera for a film shot of a character's face (close-up, over the shoulder, two shot...), aimed and sized from the face itself, on a consistent side of the line to the person they talk to, so shots and reverse shots cut together. Reports heads in the way.

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": {
      "subject": "<subject>"
    },
    "name": "camera_shot"
  }
}

Input Schema

NameRequiredDescriptionDefault
shotNoextreme_close_up (eyes and mouth), close_up (head), medium_close_up (chest up), medium (waist up), over_the_shoulder (past the partner's head), two_shot (both).close_up
sideNoWhere the subject looks on screen. auto keeps the camera on one side of the line between the two (180 degree rule).auto
angleNoDegrees between the eyeline and the camera; 0 = straight on the eyeline, 90 = profile. Default per shot.
cameraNoCamera label; created if missing.Shot
heightNocm above (+) or below (-) the eyes; above makes the subject look smaller, below more powerful.
partnerNoFigure the subject talks to; sets the eyeline. Needed for over_the_shoulder and two_shot.
subjectYesFigure whose face the shot is about.
lead_roomNoShare of the picture width the face moves away from the side it looks to; 0 centers it.
make_activeNo
focal_lengthNomm; default per shot.
max_distanceNocm; keeps the camera this close to the face (a small room, a wall behind it) with a wider lens.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, closed-world write; the description adds real context beyond that: geometry is derived from the face ("aimed and sized from the face itself"), the 180-degree line is enforced implicitly via "a consistent side of the line", and "Reports heads in the way" discloses a return value the annotations do not cover. It also notes the camera is created if missing, which matters for a mutating tool. What is missing is any statement about what existing camera state gets overwritten by the placement.

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 the core action and followed by the two facts that matter most (line consistency, occlusion report). No filler, though the parenthetical shot list is somewhat redundant with the schema enum.

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 an 11-parameter scene-mutating tool with no output schema, the description is nearly sufficient: it explains the compositional model, the continuity rule, and that the call may add a camera and report occlusion. Residual gaps are the lack of any statement about failure modes (e.g. missing partner for over_the_shoulder) and about what the call returns besides the head warning.

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 91%, so the enum meanings for shot/side and the units for angle, height, lead_room and focal_length are already documented in the schema. The description contributes the underlying principle (all framing is computed from the face and from the eyeline), which helps interpret angle/height/partner, but it does not add per-parameter nuance such as what "auto" resolves to or how two_shot behaves without a partner. Baseline 3 reflects schema doing the heavy lifting.

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 gives a specific verb and resource ("places a camera for a film shot of a character's face") and enumerates the shot vocabulary it supports ("close-up, over the shoulder, two shot"), so the agent knows exactly what the tool produces. It separates itself from camera_create/camera_set in spirit (compositional placement rather than raw camera manipulation), though it never names a sibling to anchor that distinction.

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 implied through the purpose clause "on a consistent side of the line ... so shots and reverse shots cut together", which tells the agent this is the tool for coverage geometry rather than one-off camera tweaks. There is no explicit "use X instead when..." routing, no statement of prerequisites, and no when-not to guide a choice against camera_create or camera_set.

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