Skip to main content
Glama

GreenlandAI

by ai.greenlandai
OverviewDiscussionsAdmin

funding_prepare

The in-band funding step for a joule shortfall — NEVER a website to visit (operator lock). USDC on Base is the live agent-fundable rail: deposit USDC to your own Base address (derived from your credential), at or above the live minimum (minimum_usdc, read per call from deposit-status), credited automatically when the deposit scanner sees it — track it with deposit_status. Card funding stays a human web flow. Availability is read from the running system per call (relays your deposit-address), so this never reports stale state; it does not itself move money. A GreenlandAI AGENT key (gai_) gets its OWN USDC address (greenlandai.ai/api/v1/agent/me/deposit-address — credits the agent's own wallet) plus its owner's funding route; an owner's own credential is told where its own address is.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
neededNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNo
neededNo
routesNo
wallet_idNo
in_band_agent_funding_liveNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / wallet_id
      Removed value: -{
-  "title": "Wallet Id",
-  "type": "string"
-}
    • removedInput schema / required
      Removed value: -[
-  "wallet_id"
-]
    • changedOutput schema / description
      Previous value: -"funding_prepare — authored by this relay; no backend."New value: +"funding_prepare — relays deposit-address for live USDC availability + the caller's own address."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "funding_prepare — authored by this relay; no backend.",
+  "properties": {
+    "in_band_agent_funding_live": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "In Band Agent Funding Live"
+    },
+    "needed": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Needed"
+    },
+    "note": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Note"
+    },
+    "routes": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Routes"
+    },
+    "wallet_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Wallet Id"
+    }
+  },
+  "title": "FundingPrepareOut",
+  "type": "object"
+}
  3. First observed

TDQS

B3/5.0
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 disclose meaningful behavior: USDC on Base is the agent-fundable rail, deposits are credited automatically by a scanner, state is read live per call (never stale), and the tool does not move money itself. It also distinguishes agent-key vs owner-credential handling. It stops short of stating auth requirements or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is a dense run-on packed with nested parentheticals and backticked field names, so the core action is not front-loaded and must be reconstructed. Length is large relative to the small amount of actionable instruction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because an output schema exists, return values need not be described, and the live-state and auto-credit behavior are covered. But the undefined `needed` parameter and the ambiguous 'prepare but does not move money' framing leave the agent without a fully actionable picture.

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

Parameters2/5

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

The single parameter `needed` has 0% schema description coverage and the description never explains it — it only mentions `minimum_usdc`, a different field read from deposit-status. For a tool whose one input shapes funding preparation, leaving `needed` undefined is a real gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific domain and role ('the in-band funding step for a joule shortfall') and rules out the website/card path, but the actual action it performs is genuinely hard to pin down — it both 'prepares' funding and explicitly 'does not itself move money.' An agent learns the topic but not cleanly what this call returns or changes.

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

Usage Guidelines3/5

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

Implied trigger is a joule shortfall, with `deposit_status` named for tracking and card funding marked as a separate human web flow. However there is no explicit when-not guidance and no clear statement of when to call this vs. the sibling `deposit`/`deposits` tools, so routing remains partly inferential.

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

All GreenlandAI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources