Infrastructure: Refill internal ledger. Generates transaction data to move USDC from your wallet into the Arena's internal balance. This is required to paint pixels and saves ~70% on gas.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | USDC amount as a string (e.g. '1.50') |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that this is an infrastructure operation, moves USDC into the internal ledger, and saves ~70% on gas. However, it does not explicitly state whether this is a write operation, whether user approval is needed, or what side effects occur. It does add meaningful context beyond the tool name but leaves some ambiguity around the transaction generation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with three short sentences that each add value: labeling it as infrastructure, explaining the action, and providing the usage context ('required to paint pixels') and benefit ('saves ~70% on gas'). No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with no output schema, the description covers the purpose, prerequisite, and key benefit. It mentions 'generates transaction data' which hints at the return value, but does not elaborate on how the agent should handle that data. Given the simplicity, this is reasonably complete but has a small gap regarding the output format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the parameter description ('USDC amount as a string (e.g. '1.50')') is clear. The tool description does not add further meaning beyond the schema, so the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: moving USDC from the user's wallet into the Arena's internal balance. It uses a specific verb ('move') and resource ('USDC', 'internal balance'), and distinguishes itself from the sibling tool 'withdraw_usdc' by the direction of the transfer. The mention of 'required to paint pixels' also provides context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates when to use the tool ('required to paint pixels') and implicitly contrasts with the reverse operation (withdraw_usdc), but it does not explicitly name alternatives or state when not to use it. This is clear context but lacks explicit exclusions, so a 4 is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose: reading canvas, pixel info, fees, balances, and generating transactions for deposits, withdrawals, painting, and rewards. No two tools overlap in a way that would confuse an agent.
Most tools follow a clear verb_noun pattern (get_, deposit_, withdraw_, etc.). The only minor inconsistency is 'read_canvas' instead of 'get_canvas', but the naming remains intuitive and generally consistent.
With 10 tools, the server is well-scoped for a game arena. It covers all core actions—reading state, managing balances, painting, and claiming rewards—without unnecessary redundancy or bloat.
The tool set covers the full gameplay loop: understanding rules, viewing the canvas, analyzing pixel costs, managing internal balances, executing paint intents, claiming rewards, and withdrawing profits. No critical gaps exist for the stated purpose.