Skip to main content
Glama
Sign In

SPOE

by ai.spoe
OverviewDiscussionsAdmin

Build a new app or website

create_app

Start building a new app, website or game on SPOE from a description. kind "website" makes a plain HTML site (fast, can be published at name.spoe.dev); kind "app" makes a full-stack Next.js, Fastify and Postgres app; kind "game" makes a browser game (Phaser for 2D, Three.js for 3D) that plays on a computer and a phone, can be published at name.spoe.dev, and borrows the mechanics of any games it is asked to be like, never their names, characters or art. A second AI from another model family reviews the change. Costs credits from the account: estimated first, charged when the build finishes, never if it fails. Returns the studio link to watch it and the project id for app_status.

Input Schema

NameRequiredDescriptionDefault
kindNowebsite (plain HTML), app (full stack) or game (a browser game). Default website.
nameYesA short name for the project.
descriptionYesWhat to build, in plain words: who it is for, the pages, what it should do. For a game: the kind of game, games it should be like, the controls and the goal.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / description / description
      Previous value: -"What to build, in plain words: who it is for, the pages, what it should do."New value: +"What to build, in plain words: who it is for, the pages, what it should do. For a game: the kind of game, games it should be like, the controls and the goal."
    • changedInput schema / properties / kind / description
      Previous value: -"website (plain HTML) or app (full stack). Default website."New value: +"website (plain HTML), app (full stack) or game (a browser game). Default website."
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "website",
-  "app"
-]New value: +[
+  "website",
+  "app",
+  "game"
+]
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses the credit cost model (estimated first, charged on completion, never on failure), the second-model-family review step, the IP constraint that a game borrows mechanics but never names/characters/art, and publishing to name.spoe.dev. Nothing in the annotation set (readOnly/idempotent/destructive) covers any of this.

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 dense paragraph, front-loaded with the action before the kind breakdown and cost notes. Every clause carries information, though the long compound sentences about game IP and cost sequencing slow scanning slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by stating what is returned (studio link plus project id for app_status). Costs, review behavior and kind semantics are all covered, so an agent has everything needed to invoke it correctly.

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%, so the baseline is 3, but the description adds meaning the schema does not: it explains what 'kind' produces in each case (engines, publishability) and specifies what the free-text 'description' should contain for games (kind, comparable games, controls, goal). That is above-baseline enrichment of the same parameters.

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 and resource ('Start building a new app, website or game on SPOE') and decomposes the three output kinds with distinct technical meaning. It also names the downstream sibling ('the project id for app_status'), so an agent can place it in the workflow without opening either schema.

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?

Gives clear selection criteria for the 'kind' enum (website = plain HTML and publishable, app = full-stack, game = browser game with specific engines), which is real when-to-use guidance. It stops short of stating exclusions or prerequisites relative to siblings like list_apps or check_handle, so it does not reach a 5.

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

All SPOE toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources