Skip to main content
Glama

recipebooq

by com.recipebooq
OverviewDiscussionsAdmin

Build an app from a design

emit_app
Read-onlyIdempotent

Needs a subscription. Turns an App Builder design into a working Expo app: navigation, providers, tab bar, screens and the components they use. Returns a recipe for the current project: every file with its target path, one install line and ordered steps with a check each. Pass step for one step in full, which does not count against the daily allowance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNofor step write or review; each page names the next
stepNoa step id from the recipe, or "review" for the screen list
appIdYesthe share code from the App Builder's "Send app to agent", e.g. "34ca4babb2"
overrideNoemit even with screens flagged not ready; ask the customer first

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / appId / description
      Previous value: -"the share code, e.g. \"34ca4babb2\""New value: +"the share code from the App Builder's \"Send app to agent\", e.g. \"34ca4babb2\""
    • changedInput schema / properties / override / description
      Previous value: -"emit even when screens are flagged as not ready. Ask the customer first; the flags exist for a reason."New value: +"emit even with screens flagged not ready; ask the customer first"
    • addedInput schema / properties / page
      Added value: +{
+  "description": "for step write or review; each page names the next",
+  "type": "number"
+}
    • addedInput schema / properties / step
      Added value: +{
+  "description": "a step id from the recipe, or \"review\" for the screen list",
+  "type": "string"
+}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered; the description adds real value beyond them by disclosing the subscription requirement, the daily allowance and the fact that per-step calls are exempt. It does not describe write behavior or error conditions, keeping it from a 5.

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?

Three sentences, front-loaded with the gating prerequisite and then the operation and return contract. Every sentence carries weight; only minor compression is possible.

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?

With no output schema, the description correctly summarizes the return shape (files with target paths, an install line, ordered steps with checks). Combined with the subscription and quota notes, an agent has enough to call it correctly, though error/edge behavior for invalid appId is unaddressed.

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 semantics the schema lacks: `step` yields one step in full and is exempt from the daily allowance, and it cross-references the recipe as the source of valid step ids. That is genuine meaning 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-and-resource relationship: it transforms an App Builder design into a working Expo app, then enumerates the concrete artifacts (navigation, providers, tab bar, screens, components). The return contract ('a recipe: every file with its target path, one install line and ordered steps') further distinguishes it from siblings like propose_app and verify_app.

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?

It gives a clear prerequisite ('Needs a subscription') and instructs the agent on the `step` mode including its quota behavior ('does not count against the daily allowance'). It does not explicitly route between alternatives such as propose_app or verify_app, so it falls short of a 5.

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

All recipebooq 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