Skip to main content
Glama

build

Place an extractor to mine a resource deposit or a hub to trade on your revealed Land cell. Requires prior authentication and auto-approves CPU payment.

Instructions

Place a building on a revealed Land cell you own. Requires a session — call authenticate first. Two types: extractor (mines a resource deposit — pass the targetResourceId of a resource that has an active deposit on the cell) and hub (trade — pass targetResourceId: null). Build always costs $CPU, which this tool auto-approves once (a one-time unbounded allowance) before submitting the on-chain payment and waiting for its confirmation. The building is applied by the indexer a few seconds later; an extractor then starts mining automatically — track it with get_mining_status. Inspect the cell with get_cell. A cell holds one building. An extractor may be rebuilt only on a cell whose target resource is fully depleted (claimed to zero): the new extractor — which must target a resource that still has an active deposit — replaces the old one. Otherwise the build is rejected (the existing building isn’t replaceable). A hub can only go on a cell that was never built on. A build already awaiting payment on the cell blocks a different one — pay or let it lapse first (an identical re-request just resumes it).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tokenIdYesThe tokenId of a revealed cell you own to build on.
buildingTypeYesextractor (mines a resource deposit) or hub (trade).
targetResourceIdNoFor an extractor, the resource id (2–13) to mine — it must have an active deposit on the cell. Must be null for a hub.
Behavior5/5

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

Discloses CPU cost, auto-approval, on-chain payment, indexer delay, automatic mining for extractor, replacement rules, and blocking conditions, fully compensating for missing annotations.

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?

Comprehensive but slightly lengthy; however every sentence contributes necessary information, organized logically from prerequisites to detailed behavior.

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?

Covers all aspects: prerequisites, building types, costs, timing, tracking via get_mining_status and get_cell, and edge cases like replacement and blocking, despite no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds significant meaning beyond schema: explains targetResourceId must refer to active deposit for extractor, must be null for hub, and elaborates on replacement scenarios.

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 clearly states 'Place a building on a revealed Land cell you own,' specifies two types (extractor and hub), and distinguishes from sibling tools which are unrelated actions like authenticate or buy_lot.

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

Usage Guidelines5/5

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

Explicitly requires session via `authenticate` first, describes when to use extractor (cell with active deposit) vs hub (never-built cell), and warns about blocking behavior when payment is pending.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sodiqit/cpu-game-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server