Skip to main content
Glama

t2000_send

Send USDC or stablecoins to Sui addresses or contacts using dollar amounts. Preview transactions with dry run mode before signing.

Instructions

Send USDC or stablecoins to a Sui address or contact name. Amount is in dollars. Subject to per-transaction and daily send limits. Set dryRun: true to preview without signing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYesRecipient Sui address (0x...) or contact name (e.g. 'Tom')
amountYesAmount in dollars to send
assetNoAsset to send (default: USDC)
dryRunNoPreview without signing (default: false)

Implementation Reference

  • The 't2000_send' tool is registered and implemented in 'packages/mcp/src/tools/write.ts'. It handles sending assets, supports dry runs for previews, and integrates with the agent's contacts and transaction enforcer.
    server.tool(
      't2000_send',
      'Send USDC or stablecoins to a Sui address or contact name. Amount is in dollars. Subject to per-transaction and daily send limits. Set dryRun: true to preview without signing.',
      {
        to: z.string().describe("Recipient Sui address (0x...) or contact name (e.g. 'Tom')"),
        amount: z.number().describe('Amount in dollars to send'),
        asset: z.string().optional().describe('Asset to send (default: USDC)'),
        dryRun: z.boolean().optional().describe('Preview without signing (default: false)'),
      },
      async ({ to, amount, asset, dryRun }) => {
        try {
          const resolved = agent.contacts.resolve(to);
    
          if (dryRun) {
            agent.enforcer.check({ operation: 'send', amount });
            const balance = await agent.balance();
            const config = agent.enforcer.getConfig();
    
            return {
              content: [{
                type: 'text',
                text: JSON.stringify({
                  preview: true,
                  canSend: balance.available >= amount,
                  amount,
                  to: resolved.address,
                  contactName: resolved.contactName,
                  asset: asset ?? 'USDC',
                  currentBalance: balance.available,
                  balanceAfter: balance.available - amount,
                  safeguards: {
                    dailyUsedAfter: config.dailyUsed + amount,
                    dailyLimit: config.maxDailySend,
                  },
                }),
              }],
            };
          }
    
          const result = await mutex.run(() => agent.send({ to, amount, asset }));
          return { content: [{ type: 'text', text: JSON.stringify(result) }] };
        } catch (err) {
          return errorResult(err);
        }
      },
    );
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively adds context beyond basic functionality: it specifies that the amount is in dollars, mentions per-transaction and daily send limits (important for rate limiting), and explains the dryRun option for previewing without signing. This covers key behavioral traits like constraints and safety features.

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?

The description is front-loaded with the core purpose in the first sentence, followed by important constraints and an alternative usage. Every sentence earns its place by adding critical information without redundancy. It is appropriately sized for a tool with behavioral nuances.

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?

Given the complexity of a financial transaction tool with no annotations and no output schema, the description is mostly complete. It covers purpose, constraints (limits), and a safety feature (dryRun). However, it lacks details on error conditions, response format, or authentication requirements, which could be important for an agent to handle 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?

The schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal semantic value beyond the schema: it reiterates that 'Amount is in dollars' (covered in schema) and mentions 'dryRun: true to preview without signing' (also in schema). Baseline 3 is appropriate as the schema does the heavy lifting.

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 the action ('Send'), the resources ('USDC or stablecoins'), and the destination ('to a Sui address or contact name'). It distinguishes from siblings like t2000_pay (which might be for payments) or t2000_exchange (which involves trading) by focusing specifically on sending assets to recipients.

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?

The description provides clear context for usage ('Send USDC or stablecoins to a Sui address or contact name') and includes a specific alternative usage ('Set dryRun: true to preview without signing'). However, it does not explicitly state when not to use this tool versus alternatives like t2000_pay or t2000_exchange, which could involve different transaction types.

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/mission69b/t2000'

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