Skip to main content
Glama
Cavi Character Animator MCP

Cavi Character Animator MCP

Official
by cavi-ai

capture

Takes a screenshot of only the Character Animator window and saves bounded OCR results into a new workspace directory for visual evidence without starting recording.

Instructions

Capture only the Character Animator window with bounded OCR into a new workspace directory.

Observed text/geometry are visual evidence, not native scene IDs. Never starts recording.

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": {
      "directory": "<directory>"
    },
    "name": "capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
directoryYes

Output Schema

NameRequiredDescriptionDefault
pathYes
nativeYes
sha256Yes
identityYes
launches_applicationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, closed-world operation, and the description adds real context beyond them: output lands in a *new* workspace directory, OCR is bounded, and it explicitly does not start recording. It also warns that observed text/geometry are visual evidence rather than native scene IDs, which is a meaningful reliability caveat.

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?

Three short sentences, purpose front-loaded, with the scope constraint first and the negative guarantee plus data caveat after. No filler and nothing repeated from structured fields.

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?

Output schema exists, so return structure need not be described. The definition covers action, target window, side effect (new directory), and a key semantic caveat; only the directory parameter's preconditions remain undocumented.

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?

One parameter at 0% schema coverage, so the description must carry the meaning. It does partially — the directory is a new workspace directory that receives the capture — but it does not say whether the path must not already exist, how it is named, or what happens on collision.

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 and resource — "Capture only the Character Animator window with bounded OCR into a new workspace directory" — plus a scoping qualifier ("only") that implies a narrower alternative to a general screenshot. It is clear on its own, but it does not name a sibling (e.g. inspect) to differentiate against.

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 scope: capture only the Character Animator window, and the closing "Never starts recording" excludes an adjacent expectation. However, there is no explicit statement of when to choose this over inspection/status siblings, so the agent must infer the routing.

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