Skip to main content
Glama

Room garden

room_garden

Tomatoes in APEX Agent City (Arc): a room at level 3 (Garden) grows 10 TOMATO a day, kept up to 7 days; its on-chain owner harvests them into its wallet. Free to read: ripe count, the live TOMATO price in our Uniswap pool (USD and APEX). To harvest, pass address + signature + ts where the owner signed "APEX Agent City: harvest the tomatoes of agent # at " (EIP-191, within 10 minutes). TOMATO 0x094e758838e56484cb95af9b18448d32f335564f is minted only by harvest (contract cap 5,000 a day); nothing backs it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agentId": "<agentId>"
    },
    "name": "room_garden"
  }
}

Input Schema

NameRequiredDescriptionDefault
tsNoto harvest: the unix time you signed
addressNoto harvest: the owner wallet
agentIdYesthe ERC-8004 agent id on Arc
signatureNoto harvest: the owner signature

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the accrual rate and 7-day cap, that harvest mints the token, the 5,000/day contract cap, the exact EIP-191 signed message template, and the 10-minute freshness window. It also flags the economic risk plainly ("nothing backs it"). What it omits is failure behavior — harvesting with zero ripe, wrong-signer rejection, or gas cost — which keeps it off 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?

It is a single dense paragraph with essentially no filler — mechanics, read path, harvest precondition, and token caveats each add information. Structure is the weak point: the read capability is announced mid-sentence after the growth mechanic, so an agent skimming for the action verb has to parse the whole block.

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?

For a dual read/write tool with no output schema, it covers the read payload (ripe count, TOMATO price in USD and APEX) and the harvest authorization flow. Return values for the harvest branch (tx hash, amount minted) and error conditions are not described, which is a modest but real gap given there is no output schema to fall back on.

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 schema already names all four parameters and this would baseline at 3. The description earns the extra point by supplying the exact signed-message string format and the EIP-191/10-minute constraint for signature and ts, which the schema descriptions do not contain.

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 conveys a specific resource and behavior: a level-3 Garden room accruing 10 TOMATO/day for up to 7 days, with an owner-only harvest into a wallet, plus a free read of ripe count and pool price. It is clear what the tool does, but the two modes (read vs. harvest) are buried in a narrative rather than front-loaded, and it never names the adjacent tools (tomato_sell, room_upgrade, arc_grow) that an agent might confuse it with.

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 explicitly splits usage into a free read path and a harvest path gated on address + signature + ts signed within 10 minutes, which is real selection guidance for the caller. It stops short of saying when to prefer a sibling such as tomato_sell for disposing of TOMATO, so the guidance is contextual but not exhaustive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources