Skip to main content
Glama

read.asset_manager.intents

Read-onlyIdempotent

List all available automation intents for asset management, including tool names, parameters, and supported chains. Discover which automations can be configured and how each works.

Instructions

List all available automation intents with their tool names, required parameters, and supported chains. Use this to discover which automations can be configured and what each one does. Each intent has a corresponding write.asset_manager.{id} tool that returns encoded args. To apply automations, call the intent tools then pass the combined result to write.account.set_asset_managers. All intent tools accept enabled=false to disable. Multiple intents can be combined by merging their returned arrays into a single set_asset_managers call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chain_idNoFilter to automations available on this chain. Omit to see all.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
automationsYes
shared_paramsYes
usageYes

Implementation Reference

  • Registration and handler function for the 'read.asset_manager.intents' tool. Calls server.registerTool with the name, schema, and an async handler that filters INTENTS by chain_id, hydrates dex_protocol values for the chain, and returns the list of automations with usage instructions.
    export function registerAssetManagerTools(server: McpServer) {
      server.registerTool(
        "read.asset_manager.intents",
        {
          annotations: {
            title: "List Available Automations",
            readOnlyHint: true,
            destructiveHint: false,
            idempotentHint: true,
            openWorldHint: false,
          },
          description:
            "List all available automation intents with their tool names, required parameters, and supported chains. Use this to discover which automations can be configured and what each one does. Each intent has a corresponding write.asset_manager.{id} tool that returns encoded args. To apply automations, call the intent tools then pass the combined result to write.account.set_asset_managers. All intent tools accept enabled=false to disable. Multiple intents can be combined by merging their returned arrays into a single set_asset_managers call.",
          inputSchema: {
            chain_id: z
              .number()
              .optional()
              .describe("Filter to automations available on this chain. Omit to see all."),
          },
          outputSchema: IntentsListOutput,
        },
        async (params) => {
          try {
            let filtered = INTENTS;
            if (params.chain_id !== undefined) {
              const validChainId = validateChainId(params.chain_id);
              const chainDexProtocols = getChainDexProtocols(validChainId);
              filtered = INTENTS.filter((i) => i.chains.includes(validChainId)).map((intent) => ({
                ...intent,
                required_params: intent.required_params.map((p) =>
                  p.name === "dex_protocol" ? { ...p, values: chainDexProtocols } : p,
                ),
              }));
            }
    
            const result = {
              automations: filtered,
              shared_params: ["enabled (boolean, default true)", "chain_id (number, default 8453)"],
              usage:
                "1. Call the intent tool (e.g. write.asset_manager.rebalancer) with enabled + chain_id to get encoded args. 2. Optionally merge arrays from multiple intent calls. 3. Pass to write.account.set_asset_managers to build the unsigned tx.",
            };
            return {
              content: [
                {
                  type: "text" as const,
                  text: JSON.stringify(result, null, 2),
                },
              ],
              structuredContent: result,
            };
          } catch (err) {
            return {
              content: [
                {
                  type: "text" as const,
                  text: `Error: ${err instanceof Error ? err.message : String(err)}`,
                },
              ],
              isError: true,
            };
          }
        },
      );
    }
  • Output schema (IntentsListOutput) defining the shape of the response: automations array, shared_params array, and usage string.
    export const IntentsListOutput = z.object({
      automations: z.array(z.record(z.unknown())),
      shared_params: z.array(z.string()),
      usage: z.string(),
    });
  • Input schema: optional chain_id number used to filter automations by chain.
    inputSchema: {
      chain_id: z
        .number()
        .optional()
        .describe("Filter to automations available on this chain. Omit to see all."),
    },
  • Chain constants (ALL_CHAINS = [8453, 130, 10], BASE_ONLY = [8453]) used to populate which chains each automation supports.
    const ALL_CHAINS: ChainId[] = [8453, 130, 10];
    const BASE_ONLY: ChainId[] = [8453];
  • Import and registration call (registerAssetManagerTools) that wires the tool into the MCP server.
    import { registerAssetManagerTools } from "./read/asset-managers.js";
    import { registerCreateTool } from "./write/account/create.js";
    import { registerDepositTool } from "./write/account/deposit.js";
    import { registerWithdrawTool } from "./write/account/withdraw.js";
    import { registerBorrowTool } from "./write/account/borrow.js";
    import { registerRepayTool } from "./write/account/repay.js";
    import { registerApproveTool } from "./write/wallet/approve.js";
    import { registerPoolDepositTool } from "./write/pool/deposit.js";
    import { registerPoolRedeemTool } from "./write/pool/redeem.js";
    import { registerRebalancerTool } from "./write/asset-managers/rebalancer.js";
    import { registerCompounderTools } from "./write/asset-managers/compounder.js";
    import { registerYieldClaimerTools } from "./write/asset-managers/yield-claimer.js";
    import { registerCowSwapperTool } from "./write/asset-managers/cow-swapper.js";
    import { registerMerklOperatorTool } from "./write/asset-managers/merkl-operator.js";
    import { registerSetAssetManagersTool } from "./write/asset-managers/set-asset-managers.js";
    import { registerSendTool } from "./dev/send.js";
    import { registerAddLiquidityTool } from "./write/account/add-liquidity.js";
    import { registerRemoveLiquidityTool } from "./write/account/remove-liquidity.js";
    import { registerSwapTool } from "./write/account/swap.js";
    import { registerDeleverageTool } from "./write/account/deleverage.js";
    import { registerStakeTool } from "./write/account/stake.js";
    import { registerCloseTool } from "./write/account/close.js";
    
    export function registerAllTools(
      server: McpServer,
      api: ArcadiaApiClient,
      chains: Record<ChainId, ChainConfig>,
    ) {
      // Read tools
      registerAccountTools(server, api, chains);
      registerPoolTools(server, api);
      registerAssetTools(server, api);
      registerStrategyTools(server, api);
      registerPointsTools(server, api);
      registerGuideTools(server);
      registerWalletTools(server, chains, api);
      registerAssetManagerTools(server);
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds behavioral context by stating what the tool returns (tool names, required parameters, supported chains) and mentions the ability to disable intents. No contradictions.

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?

The description is two sentences and covers purpose, workflow, and key behaviors without redundancy. It is well-structured and front-loaded with the primary action.

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?

Given the tool's simplicity (one optional parameter, read-only, output schema exists), the description fully covers usage context, including how to use it in conjunction with other tools. It is complete for an AI agent to understand and invoke the tool correctly.

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?

The input schema has one parameter (chain_id) with a clear description, and schema coverage is 100%. The description adds context about filtering by chain but does not introduce new meaning beyond the schema.

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 explicitly states 'List all available automation intents with their tool names, required parameters, and supported chains,' providing a specific verb and resource. It distinguishes itself from sibling tools by being a read-only discovery tool versus the write tools for specific intents.

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?

The description gives clear guidance on when to use this tool: to discover automations before configuring them. It explains the workflow: call intent tools, then pass combined result to write.account.set_asset_managers. It also mentions multiple intents can be combined and that intents accept enabled=false to disable.

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/arcadia-finance/mcp-server'

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