Skip to main content
Glama
TechBot_Blender_MCP

TechBot_Blender_MCP

by bharatnextai

resolve_pending_approval

Approve or deny a paused Blender scene mutation, resuming it once only when a recorded human approval token exists; denial cancels the task.

Instructions

Resume or deny a pending scene mutation task. An approval decision only resumes the task if Blender's approval registry has already recorded an explicit human approval and issued its token; resolver credentials alone never authorize a mutation. Requires the exact task_id, session_id, cryptographic single-use nonce, canonical param_hash, and decision ('approved' or 'denied'). Resumes the original pending task exactly once upon approval.

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": {
      "task_id": "<task_id>",
      "decision": "<decision>",
      "nonce": "<nonce>",
      "param_hash": "<param_hash>"
    },
    "name": "resolve_pending_approval"
  }
}

Input Schema

NameRequiredDescriptionDefault
nonceYesSingle-use cryptographic nonce issued when the task was paused.
task_idYesUnique identifier of the pending AgentTask paused in AWAITING_APPROVAL.
decisionYesResolution request: 'approved' resumes only after Blender UI approval; 'denied' cancels the task.
auth_tokenNoOptional authentication token if UMCP_AUTH_TOKEN is configured.
param_hashYesCanonical SHA-256 hash of the pending tool parameters.
session_idNoSession ID scoping the pending task.default

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it discloses the approval-registry precondition, the nonce being single-use, and that the task resumes exactly once. It omits failure behavior (wrong param_hash, reused nonce, already-resolved task) and whether denial is idempotent, which leaves meaningful gaps for a security-sensitive mutation gate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each earning its place, with the action front-loaded and the authorization caveat placed before the credential enumeration. No boilerplate or redundancy.

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 6-parameter, annotation-free mutation-resolution tool, the description covers preconditions, one-shot semantics, and required identity material. Without an output schema it should say what a successful resolution returns or how a rejected resolution is signaled, which is the remaining gap.

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 every parameter including nonce, param_hash, decision enum, and auth_token is already documented in the schema. The description restates the required set and adds only light emphasis ('exact task_id', 'cryptographic single-use nonce') rather than new semantics such as how param_hash is computed or scoped.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb pair and resource ('Resume or deny a pending scene mutation task'), and immediately clarifies what 'resume' actually means operationally. An agent can distinguish this from a status-checking sibling like check_approval_status without opening either schema.

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?

Gives a clear precondition for use: the decision only resumes if the approval registry already holds an explicit human approval and token, and 'resolver credentials alone never authorize a mutation.' It does not explicitly name the alternative (e.g. check_approval_status) or state when not to call this, so it stops short of full routing guidance.

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