Page Lemon

Set up an app

setup_app

Destructive

Sets up an app: user sign-in, private records under one path, lists from a template. Returns markup and approve_url (the Site Owner turns it on). retention (shorter erases), sign_out_all and ai_read (this AI reads entries) ask first. Owner only; Free plan: testing.

Input Schema

Name	Required	Description
`path`	No	App pages path (default /app)
`site`	Yes
`signup`	No	invite, open, or request (owner approves)
`ai_read`	No	{lists: up to 10 names or "all", members}; answers approve_url
`template`	No	Makes its app lists and plans
`retention`	No	Kept after a user leaves: member (not), 1y, 2y, 5y; shorter erases
`plan_switch`	No	Users switch plans
`request_note`	No
`sign_out_all`	No	true: signs every user out
`confirm_token`	No
`display_field`	No	Profile field shown to group peers
`notify_members`	No	{status,reply,comments}: bool
`profile_fields`	No	Sign-up fields {name, type, label, required, options}; types text, long_text, number, date, choice, phone, url

Output Schema

Name	Required	Description	Default
`status`	No
`approve_url`	No
`agent_message`	No
`confirm_token`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

addedInput schema / properties / plan_switch

Added value: +{
+  "description": "Users switch plans",
+  "type": "boolean"
+}

Changed5 schema fields changedOct 27, 2026

changedInput schema / properties / path / description

Previous value: -"Member pages path (default /app)"New value: +"App pages path (default /app)"

changedInput schema / properties / template / description

Previous value: -"Makes its member lists and plans"New value: +"Makes its app lists and plans"

addedOutput schema / properties / agent_message
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / approve_url
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / status
```
Added value: +{
+  "type": "string"
+}
```

Changed2 schema fields changedOct 27, 2026

changedInput schema / properties / retention / description

Previous value: -"member, 1y, 2y, 5y"New value: +"Kept after a user leaves: member (not), 1y, 2y, 5y; shorter erases"

addedInput schema / properties / sign_out_all / description
```
Added value: +"true: signs every user out"
```

Changed1 schema field changedOct 25, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "confirm_token": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedOct 25, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already flag destructive=true and openWorld=true, but the description adds genuinely non-obvious context: it returns markup plus an approve_url that a Site Owner must act on, and that retention shortening erases data and sign_out_all / ai_read require asking first. That approval-gated disclosure adds real value beyond the structured fields.

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?

It is short and front-loaded: the core action comes first, then the return value, then the risky options, then constraints. The telegraphic phrasing ("retention (shorter erases)... ask first") is dense and slightly cryptic but consistently information-bearing with no filler.

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

Completeness3/5

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

For a 13-parameter destructive mutation the description covers the return/approval flow well, and an output schema exists so return values needn't be explained. But the "ask first" confirmation mechanic is not tied to confirm_token, and several optional params are silent, leaving the agent to infer how to complete a call correctly.

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?

Schema description coverage is 77%, so most params are already documented. The description reinforces the highest-risk ones (retention erasing data, sign_out_all, ai_read, template-driven lists) but adds little mechanics, and several params (confirm_token, request_note, notify_members) get no mention anywhere. Baseline 3 is appropriate.

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?

The description states a specific verb and resource ("Sets up an app") and enumerates the three things it provisions: user sign-in, private records under one path, and lists from a template. This clearly distinguishes it from data-manipulation siblings like add_app_row or save_app_list, though it does not name any sibling tool explicitly.

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?

"Owner only; Free plan: testing" gives audience and plan constraints, and it notes the Site Owner must turn it on via approve_url. However, there is no explicit guidance on when to choose this over alternatives (e.g., get_app, preview_as_user) or what prerequisites must exist first, so usage is only implied.

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

All Page Lemon tools Inspect

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

Need Help?