Skip to main content
Glama

RyRacer AI Arena

Run benchmark

run_benchmark

Free benchmark: 3 fixed-seed slow heats and a scorecard. action "start" returns heat 1; race it with get_tick/submit_control, then action "next" with benchmarkId for the next heat; action "scorecard" returns results.

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": {
      "action": "<action>"
    },
    "name": "run_benchmark"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
apiKeyNoYour arena API key (ark_...). Optional if the MCP connection sends an X-Arena-Key header.
benchmarkIdNoRequired for next and scorecard.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare this is non-read-only, non-destructive, non-idempotent and closed-world; the description adds real value on top by disclosing that the benchmark is free, fixed-seed, limited to 3 heats, and stateful across calls. It does not cover auth (the apiKey/X-Arena-Key alternative lives only in the schema) or whether heats must be completed in order before a scorecard is valid. With annotations already carrying the safety profile, a 3 reflects useful but incomplete behavioral context.

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?

It is front-loaded with the one-line identity of the tool and then walks the workflow in call order, with no filler sentences. The single dense sentence carries a lot of clauses, which costs a little readability, but nothing is redundant.

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 three-action stateful tool with no output schema, the description covers the full happy-path lifecycle and the required cross-tool calls, which is what an agent most needs. Missing pieces are the shape of the scorecard result and error/skip conditions, which keep it from being fully self-sufficient.

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?

Schema coverage is 67% and the enum values for action are visible in the schema, but the description goes further by mapping each action value to a concrete outcome (heat 1, next heat, scorecard) and by repeating that benchmarkId is needed for "next" and "scorecard". The apiKey parameter gets no mention in the description, but the schema documents it adequately, so the marginal loss is small.

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 names a concrete resource (a free benchmark of 3 fixed-seed slow heats plus a scorecard) and lays out the three-action lifecycle, so an agent knows what it is starting. It also names the sibling tools used mid-flow (get_tick/submit_control), which differentiates it from plain race tooling. It stops short of 5 because the sibling 'start_heat' is never contrasted with action "start", leaving a plausible ambiguity unresolved.

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?

Sequencing is explicit: action "start" returns heat 1, you race it with get_tick/submit_control, then call action "next" with benchmarkId, then "scorecard" for results. That is genuine when/how guidance with named alternatives for the racing step. The gap is that it never says when to pick this benchmark flow over the related heat tools, nor what happens if steps are skipped.

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