Skip to main content
Glama

AINDEX

Call an agent's tools

call_agent_tools
Destructive

Run 1 to 12 of an agent's own tools now, in order, as the agent: e.g. decide to open or close a perp, set_strategy, set_quotes, get_account. Each answer comes back in the same order. Orders go through the agent's limits and the venue, and are recorded like the agent's own. get_account (as last read; input fresh: true reads it now) and get_strategy alone answer at once. A call still running after about 25 s returns a request id for get_call_result. Needs an access key that may act. On an agent your own AI or code runs, data reads count against a daily allowance (more with trade fees paid; past it, credits); trades and the agent's own account never count. A 402 answer means the day's reads are used: send trades alone, and tell the person how to add credits as the answer says (USDG on Robinhood Chain to AINDEX's credits address, or the agent's own wallet tops them up). Ask the person before placing a trade or changing a strategy for them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent": "<agent>",
      "calls": "<calls>"
    },
    "name": "call_agent_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYes
callsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare the write/destructive/open-world profile; the description adds substantial behavior beyond that: orders route through the agent's limits and the venue and are recorded as the agent's own, a ~25 s timeout returns a request id, an access key that may act is required, and reads consume a daily allowance while trades and account reads do not. The 402 recovery path (USDG on Robinhood Chain to AINDEX's credits address, or wallet top-up) is exactly the kind of operational detail annotations cannot carry.

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?

Front-loaded with the core verb, resource, and batch size, and nearly every sentence carries unique operational information. The middle sentences about allowances, 402 responses, and credit top-up are packed into long run-ons that would read better as separate points, so it loses a point for density rather than waste.

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?

For a complex, destructive, batched execution tool with no output schema and no parameter documentation, the description covers ordering, timeouts, auth, billing, and the confirmation requirement. The main remaining gap is the shape of each returned answer and the meaning of the `agent` identifier, but an agent could call this correctly from what is given.

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?

With 0% schema description coverage the description must carry the load, and it does for `calls`: an ordered array of tool names whose answers return in the same order, with examples and a note that `input` accepts something like fresh: true. The `agent` parameter is only implied ('an agent's own tools', 'access key that may act') and never explained, which keeps this from a 5.

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?

States a specific verb and resource with scope: 'Run 1 to 12 of an agent's own tools now, in order, as the agent', and names concrete examples (set_strategy, set_quotes, get_account). It is clearly distinguished from siblings list_agent_tools (enumerate) and get_call_result (retrieve a slow call), so an agent can pick the right tool without opening schemas.

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?

Gives real operating context: batching up to 12 calls in order, when a call answers immediately vs. when it yields a request id for get_call_result, and how to respond to a 402. It also sets an explicit human-in-the-loop rule ('Ask the person before placing a trade or changing a strategy'). It stops short of stating when NOT to use it versus list_agent_tools or plan_agent, so not a full 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources