Skip to main content
Glama
Cavi Character Animator MCP

Cavi Character Animator MCP

Official
by cavi-ai

scene_action

Destructive

Dispatch one fixed menu action on the current owned-project selection: add to new scene, create take from scene audio, compute lip sync, or export PNG/WAV; verify completion via fingerprint inspect.

Instructions

Dispatch one fixed menu action against the current owned-project selection.

Actions are add_to_new_scene, create_take_from_scene_audio, compute_lip_sync or export_png_wav. Copy the fingerprint from the latest inspect; scene/export completion remains unverified until inspected.

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>",
      "expected_fingerprint": "<expected_fingerprint>",
      "lease_id": "<lease_id>"
    },
    "name": "scene_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
lease_idYes
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault
actionYes
statusYes
completionYes
retry_safeYes
native_afterYes
operation_idYes
native_dispatchYes
selection_identityYes
expected_state_fingerprintYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already supply destructiveHint=true, readOnlyHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: the expected_fingerprint acts as a concurrency/staleness guard sourced from inspect, and completion of scene/export actions is asynchronous and unverified. It still never says what the destructive actions overwrite or whether they are reversible.

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?

Two tight sentences, front-loaded with the verb and resource, then the action list, then the workflow constraint. Zero filler; the only cost is that the shorthand ("owned-project selection", "fixed menu action") is compressed to the point of needing domain familiarity.

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

Completeness3/5

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 explained. But for a destructive four-action dispatcher with 0% schema coverage, leaving lease_id and per-action outcomes undocumented is a meaningful gap that the inspect-before/after note only partly offsets.

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 0%, so the description must carry all three required parameters. It explains the provenance of expected_fingerprint (copy from the latest inspect) and lists the action enum values, but lease_id is entirely undefined and none of the four actions' individual effects are described.

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?

States a specific verb ("Dispatch") and resource ("one fixed menu action") scoped to "the current owned-project selection," then enumerates the exact four permitted actions. An agent can tell this is an action dispatcher distinct from the read-only inspect/capture siblings, though it never explicitly contrasts itself with scene_export or operation_control.

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?

Implies a clear workflow: obtain the fingerprint from the latest inspect, dispatch, then re-inspect because "scene/export completion remains unverified until inspected." That is real when-to-use guidance and names the prerequisite sibling, but there are no exclusions or conditions under which an action should be preferred over a sibling tool.

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