Skip to main content
Glama
Cavi Character Animator MCP

Cavi Character Animator MCP

Official
by cavi-ai

operation_control

Inspect, resume, or verify pending copy, import, and export operations, and reconcile cancellations with explicit evidence before changing Character Animator project state.

Instructions

Inspect or continue exact pending copy/import/export operations, verify a copy, or reconcile cancellation.

continue_export resumes only the journaled Export Scene/Go To chooser and output directory. continue_import never replays File > Import and requires the existing chooser, except for the single recorded pre-menu focus rejection. confirm_cancelled_import requires explicit user attestation and matching process/root/source evidence; it issues no native command and is not native-verified cancellation. cancel_unsubmitted applies only to an observed unsubmitted Save As chooser. reconcile_unsubmitted_copy records only a closed, pre-submit initial Save As stage after stable source checks; it sends no native command and does not imply user cancellation. reconcile_copy_after_exit resolves only a submitted initial Save As after the exact app process has exited, no matching app instance is running, and the original destination remains absent; it verifies no copy. abandon_after_exit archives an unknown operation on a first-hand owned project only after two stable observations confirm the original app process and all Character Animator instances have exited. It preserves project files and records the native outcome as unknown.

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": {
      "action": "<action>",
      "operation_id": "<operation_id>"
    },
    "name": "operation_control"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
lease_idNo
operation_idYes
user_confirmed_cancelledNo

Output Schema

NameRequiredDescriptionDefault
nativeYes
statusYes
retry_safeYes
operation_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only supply the readOnly/destructive/openWorld triad, and the description goes well beyond it with side-effect disclosure per action: confirm_cancelled_import 'issues no native command and is not native-verified cancellation', reconcile_unsubmitted_copy 'sends no native command and does not imply user cancellation', reconcile_copy_after_exit 'verifies no copy', and abandon_after_exit 'preserves project files and records the native outcome as unknown'. These are exactly the non-obvious consequences an agent cannot infer from the annotations. It also establishes ordering requirements (two stable observations, process exited, destination absent).

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?

The summary sentence is front-loaded and the remaining text is one clause per action, so every sentence carries a real constraint rather than filler. It is dense and formatted as an unbroken block, which makes it slower to scan than a per-action list, but no sentence is redundant.

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?

An output schema exists, so return values need not be described, and the description covers preconditions and side effects for nearly all ten actions. What is missing for a tool this stateful is the operation_id/lease_id lifecycle — how a pending operation is discovered and leased before this tool is called — which an agent needs to invoke it 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 carry all parameter meaning. It does document the semantics of the most important parameter, action, effectively enumerating when each of the ten values applies. However, operation_id and lease_id are never explained (what a lease is, whether inspect requires one, how operations are obtained), and user_confirmed_cancelled is only obliquely referenced via 'explicit user attestation'.

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 opening sentence gives specific verbs and a bounded resource: 'Inspect or continue exact pending copy/import/export operations, verify a copy, or reconcile cancellation.' The word 'exact' signals the journaled-operation scope, which separates it from the broader 'inspect' sibling. It stops short of naming any sibling or contrasting its scope with 'export_inspect' or 'inspect', so it is clear but not sibling-differentiated.

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?

Each action gets an explicit precondition and, in several cases, an exclusion: continue_import 'never replays File > Import', cancel_unsubmitted applies 'only to an observed unsubmitted Save As chooser', confirm_cancelled_import 'requires explicit user attestation and matching process/root/source evidence'. That is real when-to-use guidance for a multi-action tool. The gap is that it never routes the agent away from the generic 'inspect' or 'export_inspect' siblings for overlapping inspection needs.

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