Skip to main content
Glama
Cavi Character Animator MCP

Cavi Character Animator MCP

Official
by cavi-ai

import_media

Destructive

Submits a hash-pinned workspace PSD puppet or WAV to an owned project; for WAVs, verify the project's Audio row because a handoff receipt does not confirm import.

Instructions

Submit a hash-pinned workspace PSD puppet or WAV to the owned project.

PSDs use the native Import chooser. WAVs are handed to the already-running app; verify the project's Audio row because a handoff receipt does not confirm import.

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": {
      "source": "<source>",
      "kind": "<kind>",
      "lease_id": "<lease_id>"
    },
    "name": "import_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
sourceYes
lease_idYes

Output Schema

NameRequiredDescriptionDefault
kindYes
nativeYes
sourceYes
statusYes
completionYes
retry_safeYes
import_copyYes
operation_idYes
source_identityYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

Annotations only declare destructiveHint=true and readOnlyHint=false; the description adds genuinely useful behavior beyond that — PSDs go through a native Import chooser (interactive UI dependency), WAVs are handed to an already-running app, and a handoff receipt is not proof of import, so the Audio row must be verified. The main omission is that with destructiveHint=true it never says what is overwritten or that source must be hash-pinned against the project to avoid replacing existing assets.

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 tight sentences, front-loaded with the action and target, followed by per-kind behavior and the verification caveat. No filler, though the phrasing is dense and the 'already-running app' clause could be folded into the handoff statement.

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, and the per-kind behavioral notes are a real strength. However, a destructive three-parameter tool with zero schema coverage should at least describe 'lease_id' and the overwrite/destructive consequences of importing, which are absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden. It hints that 'source' is a hash-pinned workspace artifact and that 'kind' selects PSD vs WAV, but 'lease_id' is never mentioned at all and the source format (path? hash? both?) is never specified, leaving a required parameter entirely opaque.

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?

Names a specific action (import/submit) and two concrete resource types (hash-pinned workspace PSD puppet, WAV) with a clear destination (the owned project). The two-mode split is explicit, so an agent knows exactly what lands where; it stops short of contrasting with siblings like export_ingest or inspect.

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 by 'the owned project' and the two media kinds, which tells the agent this is an ingest step for an already-prepared project. There is no explicit when-to-use versus when-not, and no sibling alternative is named for cases like inspecting or validating media first.

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