Skip to main content
Glama
pico-bay

pico-bay

Official

Open or stop the pico-bay web UI

pico_ui

Open the pico-bay web interface for files, console, backup, and firmware installs, starting its server when needed; use stop to end a server this tool started.

Instructions

Open the pico-bay web UI (files, console, backup, firmware install) in the browser, starting its web server when needed (action open, the default). When pico-bay runs on a Raspberry Pi or another remote machine it cannot open the user's browser: the result then has opened: false, and url is the address to open in a browser on the user's computer. Action stop stops a web server this tool started; the pico-bay app itself is never stopped.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pico_ui"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoopen (default) or stop.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.9.40

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false) it discloses that the tool starts a web server on demand, that stop only affects a server this tool started, and that the pico-bay app itself is never stopped — a crucial blast-radius limit for a mutating tool. It also documents the remote-host outcome shape (opened: false plus url) that the agent must handle.

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?

Two dense sentences with the primary action and default first, then the remote-host caveat, then the stop semantics. Nothing is redundant with the schema or annotations.

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?

With no output schema, the description proactively explains the only return fields that matter (opened and url) and covers the remote-machine failure path. For a one-parameter tool this is fully sufficient to invoke and interpret 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% with an enum, so the baseline is 3, but the description adds real meaning: open is the default when no action is given, and stop has a narrowly defined scope. That goes beyond the schema's terse 'open (default) or stop.'

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 opens with a specific verb and resource ('Open the pico-bay web UI') and enumerates the surfaces it exposes (files, console, backup, firmware install), plus a second mode (stop). No sibling tool touches a web UI, so the agent can distinguish it immediately from the board/file/install tools.

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 states the default action (open), the exact condition for stop ('stops a web server this tool started'), and the remote-host fallback where the user must open the returned url manually. It does not name sibling alternatives, but none of the listed siblings overlap in purpose, so the practical guidance is clear.

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