Skip to main content
Glama

Jabbertoon cartoon studio

by com.jabbertoon
OverviewDiscussionsAdmin

Check a Jabbertoon program, character, pack or cartoon

validate
Read-only

Checks a Jabbertoon block program (a move, a scene or a cartoon), a character, a pack, or a saved cartoon file with Jabbertoon's own validator, the same checks the studio, the character creator and the block editor make. Give exactly one of program, character, pack or cartoon. A talking cartoon is {"cast": {"dog": {"name": "Biscuit", "look": {"template": "dog"}}}, "program": {"v": 1, "kind": "cartoon", "scripts": [{"hat": {"on": "scene", "name": "Hello"}, "body": [{"op": "say", "who": "dog", "text": "Hi!"}]}]}}: the cast is an object keyed by ids, who names a cast id, every script starts with a scene hat, and a scene's blocks are say {who, text}, does {who, behaviour} (a move id from list_moves, or an inline move), enter, exit, place, cut, caption and mood, with wait, repeat and together. A move is a program of kind "behaviour" (get_move gives ready-made ones). The answer has ok, error_count, warning_count, and the errors and warnings (the first 50 of each, in order) as {code, where, says, fix}: where is the path of the field (e.g. scripts[0].body[2]), says is what is wrong, fix is how to fix it there when the checker knows, keeping the block's own words, speaker and fields. Fix the errors and call validate again until ok is true; warnings do not stop a program from playing, but say what the site will not do: hats that never fire on jabbertoon.com today (touch, beat, loud, every) or only in the block editor (key, click), moves that do not exist, and looks it cannot draw. Nothing you send is stored or logged.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
packNoA whole pack: the manifest (pack, id, type, version, name, author, license, remixable, derived_from, content_hash) and its content. The format: https://jabbertoon.com/docs/packs/
cartoonNoA saved cartoon file: {"cast": {"<id>": {"name", "look": {"template", "style", "shape", "colors"}, "at": {"x", "y", "h", "facing"}}}, "places"?, "program"}, where program is a kind "cartoon" program. list_characters returns a whole one (cartoon_example).
programNoA block program: {"v": 1, "kind": "behaviour" | "scene" | "cartoon", "scripts": [...]}, as get_move returns. A move is kind "behaviour". The language: https://jabbertoon.com/docs/language/
characterNoA character of your own, as share_link takes it: {"name": "...", "content": {...}}, the content of a character pack (tree, legs, kind, height, footprint, ...), or a whole character pack. Its tree is checked part by part. The format: https://jabbertoon.com/docs/packs/

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesTrue when there are no errors.
urlYesThe page that describes this format.
kindNoThe program's kind (behaviour, scene, cartoon), character, or the pack's type.
errorNo
notesNo
errorsNoThe errors, in order: the first 50 at most (error_count says how many there are).
checkedNoWhat was checked: program, character, pack or cartoon.
warningsNoThe warnings, in order: the first 50 at most (warning_count says how many there are).
error_countNoHow many errors the checks found.
warning_countNoHow many warnings the checks found.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered, yet the description still adds real behavior: 'Nothing you send is stored or logged,' the distinction that warnings do not stop playback, and concrete examples of what warnings flag (dead hats, missing moves, undrawable looks). It goes beyond the annotations rather than restating them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first clause, but the body is one very long paragraph that inlines an entire cartoon JSON example and re-narrates language details already linked in the schema docs. It is information-dense but poorly chunked and heavier than needed for selection.

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?

For a complex, nested-schema tool with an output schema present, the description is thorough: it explains what gets validated, the one-of-four constraint, the retry workflow, warning semantics, and privacy behavior. Return-value details are correctly left to the output schema, leaving little an agent needs that is missing.

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

Parameters4/5

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

Schema coverage is 100% and each parameter already carries format docs, so the baseline is 3; the description adds genuine value by supplying a worked cartoon example, clarifying 'who names a cast id' and that scripts start with a scene hat, which deepens understanding of the nested structures beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Checks) and enumerates exactly what resources are validated: a block program, character, pack, or saved cartoon file. It ties itself to 'Jabbertoon's own validator' and clarifies it runs the same checks as the studio/creator/editor, so an agent can place it immediately against siblings like get_move or list_moves.

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?

Explicitly instructs 'Give exactly one of program, character, pack or cartoon' and gives a workflow: 'Fix the errors and call validate again until ok is true.' It also points to get_move for ready-made moves. It lacks explicit when-not guidance, but the mutual-exclusion rule and retry loop are strong, actionable context.

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

All Jabbertoon cartoon studio toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources