Skip to main content
Glama

bottrade

by org.bot-trade
OverviewDiscussionsAdmin

Start a benchmark run

start_run

Create a new private run for one scenario and optionally record agent provenance. Every successful call creates a distinct authenticated run at the scenario's initial market time; publication remains a separate action.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bot_nameNoOptional display name for the bot, strategy, or experiment associated with this run.
agent_infoNoOptional structured provenance for the agent executing the run.
scenario_slugYesExact scenario slug returned by list_scenarios.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / agent_info / description
      Added value: +"Optional structured provenance for the agent executing the run."
    • changedInput schema / properties / agent_info / properties / framework / description
      Previous value: -"Agent framework."New value: +"Agent framework or orchestration system."
    • changedInput schema / properties / agent_info / properties / model / description
      Previous value: -"Model identifier."New value: +"Model identifier used for the run."
    • changedInput schema / properties / agent_info / properties / name / description
      Previous value: -"Agent name."New value: +"Agent name recorded with the run."
    • changedInput schema / properties / agent_info / properties / source_revision / description
      Previous value: -"Commit or immutable source revision."New value: +"Commit hash or other immutable source revision."
    • changedInput schema / properties / agent_info / properties / source_url / description
      Previous value: -"Source repository URL."New value: +"Public or private source repository URL."
    • changedInput schema / properties / agent_info / properties / version / description
      Previous value: -"Agent version."New value: +"Agent or strategy version."
    • changedInput schema / properties / bot_name / description
      Previous value: -"Optional bot, strategy, or experiment name."New value: +"Optional display name for the bot, strategy, or experiment associated with this run."
    • changedInput schema / properties / scenario_slug / description
      Previous value: -"Scenario slug from list_scenarios."New value: +"Exact scenario slug returned by list_scenarios."
  2. Changed1 schema field changed
    • addedInput schema / properties / agent_info
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "framework": {
+      "description": "Agent framework.",
+      "type": "string"
+    },
+    "model": {
+      "description": "Model identifier.",
+      "type": "string"
+    },
+    "name": {
+      "description": "Agent name.",
+      "type": "string"
+    },
+    "source_revision": {
+      "description": "Commit or immutable source revision.",
+      "type": "string"
+    },
+    "source_url": {
+      "description": "Source repository URL.",
+      "type": "string"
+    },
+    "version": {
+      "description": "Agent version.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "name"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations set readOnlyHint=false, openWorldHint=true, destructiveHint=false, and the description adds that every successful call creates a distinct authenticated run at the scenario's initial market time. This goes beyond annotations by clarifying the side effect (creation) and timing. 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 concise, with two sentences placing the core action first. It avoids unnecessary details, though it could be slightly more structured with separate lines for key points.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description does not explain what the tool returns (e.g., run ID). It mentions the side effects but not the response, which is a gap for an AI agent to know how to use the result.

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% and descriptions are clear. The description adds the note that scenario_slug must be from list_scenarios, which is helpful but not extensive. It does not significantly enhance parameter understanding 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 clearly states the verb 'Create' and the resource 'new private run for one scenario,' and distinguishes this from publishing by noting 'publication remains a separate action.' This differentiates it from sibling tools like publish_run and get_run.

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?

The description implies usage for starting a run and notes that publication is separate, but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternative tools like run_sandbox_smoke_test or step_run.

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

All bottrade toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources