Skip to main content
Glama
Tarmac MCP

Tarmac MCP

Official
by tarmacagent

Start a Tarmac run

tarmac_start_run

Starts an isolated simulated wallet test run on a Robinhood Chain fork or fixture market, executes a USDG swap with a slippage stop, and returns the run ID plus trace link.

Instructions

Start a new test run: an isolated simulated wallet on Robinhood Chain (live fork or fixture market). The run's instruction is: swap 100 USDG for the token, stop if slippage would exceed the limit. Returns the run id and a link to the trace.

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": {
      "scenario": "<scenario>"
    },
    "name": "tarmac_start_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNofork = live Robinhood Chain state; fixture = deterministic marketfixture
tokenNoToken to buy with USDGWETH
scenarioYesMarket condition: deep pool or thin pool
agentNameNoName shown in the tracemcp-agent

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Only openWorldHint is supplied, so the description carries most of the burden and mostly delivers: it discloses that a new isolated simulated wallet is created, that state is either live-forked or deterministic fixture, and that the call returns a run id and a trace link (valuable since no output schema exists). It omits whether runs persist, time out, or consume quota, and whether fork mode touches real chain state beyond reads.

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?

Two short sentences, front-loaded with the action and environment, then the return values. The embedded run instruction ('swap 100 USDG for the token, stop if slippage would exceed the limit') is slightly ambiguous about whether it is a fixed behavior or an example, which is the only real source of friction.

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 four-parameter creation tool with no output schema and only one annotation, the description covers environment, isolation, modes, and return payload well enough to call it correctly. Residual gaps are operational (run lifecycle, resource implications), not blockers to invocation.

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 100% with enum documentation for mode, token, and scenario, so the schema already does the heavy lifting and the baseline applies. The description paraphrases mode ('live fork or fixture market') and token usage ('swap 100 USDG for the token') but adds nothing about agentName or about how the scenario values map to the described stop condition.

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

Purpose4/5

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

The description gives a specific verb and resource ('Start a new test run') plus the concrete environment ('isolated simulated wallet on Robinhood Chain, live fork or fixture market'), which is much more than a restatement of the title. It does not explicitly name a sibling or contrast itself with tarmac_get_run or tarmac_finish, so it stops short of the top band.

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?

Usage is implied rather than stated: 'start a new test run' signals that this is the entry point before get_run/attach/finish, and the embedded instruction suggests what the run will do. There is no explicit when-not guidance, no prerequisite statement, and no pointer to the sibling tools for follow-up steps.

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