Skip to main content
Glama

recipebooq

by com.recipebooq
OverviewDiscussionsAdmin

Add a screen to an app

add_screen
Read-onlyIdempotent

Needs a subscription. Adds one screen designed in the App Builder to a project. With the project's .opointo/files.json it returns the screen file, the route that mounts it and the one line to register it, and never rewrites existing files. Without it, a self-contained screen file for any Expo app.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tabNonest it in this tab's stack; omit to place it where the design does
appIdYesthe share code from "Send app to agent"
screenNothe new screen's name in that design
manifestNothe parsed .opointo/files.json
componentNameNoonly to add a second copy of a screen; omit for the export's name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / componentName / description
      Previous value: -"e.g. \"InvoiceScreen\""New value: +"only to add a second copy of a screen; omit for the export's name"
    • changedInput schema / properties / tab / description
      Previous value: -"nest it in this tab's stack; omit for the root, which covers the tab bar"New value: +"nest it in this tab's stack; omit to place it where the design does"
  2. Changed7 schema fields changed
    • addedInput schema / properties / appId
      Added value: +{
+  "description": "the share code from \"Send app to agent\"",
+  "type": "string"
+}
    • changedInput schema / properties / componentName / description
      Previous value: -"React component name, e.g. \"InvoiceDetail\". Defaults to GeneratedScreen."New value: +"e.g. \"InvoiceScreen\""
    • removedInput schema / properties / compositionId
      Removed value: -{
-  "description": "share code for the new screen, from the App Builder",
-  "type": "string"
-}
    • changedInput schema / properties / manifest / description
      Previous value: -"the parsed .opointo/files.json from the project root"New value: +"the parsed .opointo/files.json"
    • addedInput schema / properties / screen
      Added value: +{
+  "description": "the new screen's name in that design",
+  "type": "string"
+}
    • changedInput schema / properties / tab / description
      Previous value: -"nest it in this tab's stack so the tab bar stays visible. Omit to put it at the root, where it covers the tab bar (right for a modal)."New value: +"nest it in this tab's stack; omit for the root, which covers the tab bar"
    • changedInput schema / required
      Previous value: -[
-  "compositionId",
-  "manifest"
-]New value: +[
+  "appId"
+]
  3. Changed1 schema field changed
    • changedInput schema / properties / manifest / description
      Previous value: -"the parsed .recipebooq/files.json from the project root"New value: +"the parsed .opointo/files.json from the project root"
  4. Changed1 schema field changed
    • changedInput schema / properties / compositionId / description
      Previous value: -"share code for the new screen, from the composer"New value: +"share code for the new screen, from the App Builder"
  5. Added

TDQS

B3.2/5.0
Behavior1/5

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

The description says the tool 'Adds one screen designed in the App Builder to a project' and 'never rewrites existing files,' which implies a write operation creating or modifying files. This contradicts the readOnlyHint=true annotation, which declares the tool does not modify its environment. Even though it later says it 'returns the screen file,' the initial framing is inconsistent with the annotation.

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?

The description is reasonably concise and front-loads the subscription requirement and core action. It could be structured more clearly (e.g., separating prerequisites from behavior), but it avoids waste.

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?

Given the tool's complexity (5 parameters, nested object, no output schema) and the rich annotations, the description covers the subscription requirement, return values, two operational modes, and file-safety behavior. It is nearly complete, though it fails to resolve the read-only tension cleanly.

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. The description adds meaning beyond the schema by explaining the effect of the manifest parameter: with it, the tool returns the screen file, route, and registration line; without it, a self-contained screen file. This clarifies the two invocation modes.

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?

States a specific verb and resource: 'Adds one screen designed in the App Builder to a project.' It does not differentiate from sibling tools like propose_screen or emit_app, and the verb 'Adds' creates some ambiguity, but the core purpose is clear.

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

Usage Guidelines3/5

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

Implies usage via the subscription prerequisite and the two modes based on whether .opointo/files.json is supplied, but it does not name alternatives (e.g., propose_screen) or explicitly say when not to use this tool. Guidance is present but incomplete.

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