Skip to main content
Glama

axint.schema.compile

Read-onlyIdempotent

Compile minimal JSON schemas directly to Swift for intents, views, components, widgets, and apps.

Instructions

Compile a minimal JSON schema directly to Swift, bypassing the TypeScript DSL entirely. Supports intents, views, components, widgets, and full apps via the 'type' parameter. Uses ~20 input tokens vs hundreds for TypeScript — ideal for LLM agents... Use: use for token-light JSON-to-Swift generation; use compile for full TypeScript DSL control. Effects: read-only Swift generation; writes no files and uses no network.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeYesWhat to compile. Determines which other parameters are relevant: intent uses params/domain/title; view uses...
nameYesPascalCase name, e.g., 'CreateEvent' for intents, 'EventListView' for views, 'StepsWidget' for widgets. Used...
titleNoHuman-readable title shown in Shortcuts/Spotlight. Intent only. E.g., 'Create Event'. Defaults to a...
descriptionNoDescription of what this intent/view/widget does. Shown to users in system UI for intents. Optional but...
componentKindNoComponent only. Optional known component shape. Use cardArchetypes for a multi-component card kit, or omit...
tokenNamespaceNoOptional Swift token enum generated by axint.tokens.ingest, e.g., 'SwarmTokens'. Generated views/components...
domainNoApple App Intent domain. Intent only. One of: messaging, productivity, health, social, finance, commerce,...
paramsNoIntent only. Parameter definitions as { fieldName: typeString }. E.g., { recipient: 'string', amount:...
propsNoView only. Prop definitions as { fieldName: typeString }. E.g., { title: 'string', count: 'int' }. Same type...
stateNoView only. State variable definitions as { fieldName: { type: 'string', default?: value } }. Generates...
bodyNoView/widget only. Raw SwiftUI code for the body, e.g., 'VStack { Text("Hello") }'. Wrapped in the struct...
displayNameNoWidget only. Human-readable name shown in the widget gallery. E.g., 'Daily Steps'. Defaults to a spaced...
familiesNoWidget only. Supported widget sizes: systemSmall, systemMedium, systemLarge, systemExtraLarge,...
entryNoWidget only. Timeline entry fields as { fieldName: typeString }. E.g., { steps: 'int' }. Do not include...
refreshIntervalNoWidget only. Timeline refresh interval in minutes. E.g., 30 for half-hourly updates. Defaults to 60.
platformNoOptional target Apple platform hint for view/widget generation. Use macOS when the host project is a Mac...
scenesNoApp only. Scene definitions for the @main App struct. At least one scene with kind 'windowGroup' is...
formatNoWhen true (default), pipes generated Swift through swift-format with Axint's house style. Falls back to raw...

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesPrimary Axint tool response text, matching the first text content block.
isErrorNoWhether Axint marked the tool response as an error.
Behavior5/5

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

Annotations already indicate read-only and idempotent. Description adds: 'Effects: read-only Swift generation; writes no files and uses no network.' This provides concrete behavioral context beyond annotations without contradiction.

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?

Single paragraph front-loads core purpose, then lists supported types, efficiency note, usage instruction, and effects. Every sentence adds value, no wasted words.

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?

Despite complexity (18 params, nested objects, output schema), the description covers core functionality, usage, and effects. Could mention output format but output schema exists. Adequate for agent selection.

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?

Input schema has 100% description coverage across 18 parameters. The description mentions the 'type' parameter and its five kinds but adds little beyond the schema's own descriptions. Baseline 3 applies.

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?

The description clearly states it compiles JSON schema directly to Swift, bypassing the TypeScript DSL, and lists supported output types (intents, views, etc.). This distinguishes it from sibling tool axint.compile which uses TypeScript.

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

Usage Guidelines5/5

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

Explicit guidance: 'Use: use for token-light JSON-to-Swift generation; use compile for full TypeScript DSL control.' Also highlights token efficiency for LLM agents, making when-to-use clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/agenticempire/axint'

If you have feedback or need assistance with the MCP directory API, please join our Discord server