Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

detect_semantic_landmarks

Detect semantic anatomical landmarks like snout, horn, wing, and tail points from calibrated silhouettes or mesh curvature, project them to surface vertices, and optionally save them on the mesh.

Instructions

Automatically detect semantic anatomical landmarks (snout, horn apices, wing apices, tail tip) from calibrated reference silhouettes or mesh boundary curvature, project to closest surface vertices, and optionally persist them into the target mesh datablock.

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": {
      "target_object": "<target_object>"
    },
    "name": "detect_semantic_landmarks"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewsNoOptional list of calibrated reference views for 2D silhouette contour extrema detection.
task_idNoOptional task or workflow identifier.
approvedNoDEPRECATED / UNTRUSTED: Client-supplied approval flags in tool arguments are not trusted.
object_nameNoAlias for target_object.
store_on_meshNoWhether to store the detected landmarks in target object's custom properties (_umcp_semantic_landmarks).
target_objectYesName of the target mesh object in the Blender scene.
landmark_typesNoList of anatomical landmark types to detect. Defaults to standard dragon features.
detection_methodNoAlgorithm for feature detection: 'CONTOUR_EXTREMA' from silhouette, 'BOUNDING_PROJECTION' from view-aligned bounds, or 'CURVATURE_PEAKS' from mesh geometry.CONTOUR_EXTREMA
enforce_symmetryNoEnforce bilateral symmetry across sagittal X axis for paired landmarks (horn, wing, claws).
max_vertex_distanceNoMaximum 3D distance allowed when projecting landmark rays onto target mesh vertices.
confidence_thresholdNoMinimum confidence threshold to include a detected landmark.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does disclose the pipeline (detect from silhouette/curvature, then project onto closest surface vertices) and the conditional side effect of persisting results into the mesh datablock, which maps to the destructive aspect of store_on_mesh. It omits important behavioral facts: whether existing landmarks are overwritten, what happens when no landmark passes the confidence threshold, and whether detection is deterministic.

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?

One dense sentence, front-loaded with the verb and resource, moving logically from detection to projection to persistence. It is efficient with no filler, though the sentence is long enough that the optional-persistence clause could be split out for scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is an 11-parameter tool with no annotations and no output schema, so the description is the only place an agent can learn both behavior and results. It never says what is returned (landmark coordinates, confidence values, a success/failure summary), does not state what happens on the mesh when store_on_mesh is true versus false, and omits prerequisites and overwrite semantics, leaving significant gaps for the tool's complexity.

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 100%, so the description is not required to document parameters and a baseline of 3 is appropriate. It does add light meaning by linking 'persist them into the target mesh datablock' to store_on_mesh and by naming the two detection sources that correspond to detection_method values, but the 11 parameters' semantics (confidence_threshold, enforce_symmetry, max_vertex_distance, weights) are left entirely to the schema.

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 uses a specific verb and resource ('detect semantic anatomical landmarks') and enumerates the landmark families (snout, horn apices, wing apices, tail tip), plus names both input sources (calibrated reference silhouettes, mesh boundary curvature). It does not, however, differentiate itself from near-name siblings like configure_semantic_landmarks or inspect_semantic_landmarks, so an agent still has to infer that this is the detection step rather than configuration or inspection.

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: 'from calibrated reference silhouettes or mesh boundary curvature' hints that reference views must already be calibrated (presumably via calibrate_reference_views), but no prerequisites, when-not-to-use conditions, or alternative tool routing are stated. An agent would need to guess whether to call this before or after configure_semantic_landmarks.

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