Skip to main content
Glama

compile_and_save_project

Compiles accumulated frames, rigs, and layers into a final .stykanimate or JSON file and writes it to the specified local output path.

Instructions

Bundles the accumulated project state, frames, rigs, and layers into a final .stykanimate or valid project JSON string, writing it cleanly to a local path specified by the user.

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": {
      "outputPath": "<outputPath>"
    },
    "name": "compile_and_save_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoOutput packaging format: "json" (standard JSON), "styk-container" (binary v1 container), or "auto" (detected from extension)
prettyNoWhether to pretty-print JSON files with 2-space indentation (default: true)
outputPathYesDestination file path (e.g. "./output/my_animation.stykanimate" or "./scene.styk")

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden. It discloses that this is a filesystem write to a local path and mentions the output artifacts, but says nothing about overwriting an existing file, permission or directory-creation behavior, failure modes, or what is returned on success — material gaps for a write tool.

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?

A single front-loaded sentence with the action verb first. Slight padding remains: 'specified by the user' is redundant given the required outputPath, and 'cleanly' conveys no verifiable behavior.

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?

For a 3-parameter write tool with no annotations and no output schema, the definition covers what is produced and where, but omits overwrite semantics, prerequisite state, and the return value. An agent could call it, but must guess at the side effects of an existing destination file.

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 100%, so the schema already explains outputPath, format enum, and pretty. The description adds only the loose mapping between '.stykanimate' output and the styk-container format, without elaborating on format/extension interactions. Baseline 3 applies.

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?

Specific verb+resource: bundles accumulated project state, frames, rigs and layers and writes a .stykanimate or project JSON file. An agent can tell this is the serialization/compile step. It does not distinguish itself from the sibling render_and_export_media, which is a plausible source of confusion for an export-adjacent tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, no prerequisites (e.g. a project must already exist), and no named alternative. The phrase 'accumulated project state' only implicitly signals this is a final step, leaving the agent to infer the ordering relative to create_animation_project and render_and_export_media.

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