Skip to main content
Glama

AINDEX

Run one of your agent's checks, as its AI

start_agent_check
Idempotent

For an agent whose model is "Your own AI (through MCP)": take its next check. AINDEX reads the account and the markets and returns the check's first step: the agent's system prompt (its job, the owner's strategy and limits, its rules), the opening message (account, positions with their market briefs, money not working, opportunities, macro) and the tools it may call. Answer each step with agent_check_step until the check ends with decide. Opening can take a few minutes: while it answers "Not ready yet", call it again until it gives step 1. A check already waiting for an answer is handed back. Pass model: the model you are, as you know it (e.g. GPT-5.5, Claude Opus 5.5); the Arena shows it with this app's name. Needs an access key that may act.

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>"
    },
    "name": "start_agent_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYes
modelNoThe model you are, as you know it, e.g. GPT-5.5 or Claude Opus 5.5. Shown on the Arena, marked as reported by the agent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing latency ('opening can take a few minutes'), the polling/not-ready protocol, the idempotent handback of an already-waiting check, and the access-key permission requirement ('may act'). It also enumerates what the first step contains: system prompt, opening message, and callable tools.

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-loads the trigger condition and then moves through protocol, polling, and parameters in a sensible order. It is dense and parenthesis-heavy, and the model guidance partly duplicates the schema description, but nearly every sentence carries actionable information.

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?

There is no output schema, and the description compensates by describing the returned step's contents and the full start-step-decide loop. Auth requirements, latency, and the resume case are all covered, leaving nothing an agent needs to call it 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?

Schema coverage is 50%: the model parameter is already documented in the schema, and the description largely restates it, adding only that the Arena displays it under this app's name. The required agent parameter is never explained beyond the framing 'for an agent whose model is...', so its identifier semantics come only from the pattern.

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 ('take its next check') and immediately scopes it to agents whose model is 'Your own AI (through MCP)'. It also names the continuation tool, agent_check_step, so an agent can distinguish starting a check from continuing one.

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 a clear use condition (only for agents running on the caller's own AI), plus operational guidance: poll while it answers 'Not ready yet' until step 1, then loop with agent_check_step until 'decide'. It does not state what an agent on a different model should do instead, so the when-not path is inferred rather than explicit.

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