Skip to main content
Glama

Run

sandbase_run
Destructive

Execute a model, API, or Agent Service. Sync models return the result directly; async models (image/video/audio jobs) return status running with a run_id — poll sandbase_run_get for the output. Services require arguments.idempotency_key and optionally input; reuse the same key and input on retries. Service acceptance is not completion: poll sandbase_run_get with service_id and run_id. Omit the MCP task parameter for Services.

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": {
      "name": "<name>",
      "arguments": "<arguments>"
    },
    "name": "sandbase_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesModel name, tool name, or Agent Service ID (svc_...) to execute.
argumentsYesInput matching the inspected schema. For Services: {idempotency_key: string, input?: string}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety bar is lower, yet the description still adds real behavior: async calls return a running status with a run_id rather than the result, and Service acceptance is explicitly not completion. The main gap is that it never explains why this is flagged destructive or what side effects/costs execution can incur, and the supplied idempotency key coexisting with idempotentHint=false is not reconciled.

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?

Four sentences, front-loaded with the core action and then branching into sync, async, and Service behavior; almost no filler. The closing line 'Omit the MCP task parameter for Services' is terse and references a parameter that appears nowhere in the input schema, which slightly hurts scannability.

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 two-parameter but multi-modal tool with no output schema, the description covers the critical unknowns: what comes back on sync vs async, how to retrieve async output, and the Service idempotency/polling contract. It stops short of covering failure modes, permissions, or what the opaque MCP 'task parameter' actually is, which keeps it from being fully self-contained.

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 100%, so the baseline is 3, but the description earns above baseline by explaining that arguments must match the inspected schema and, for Services, carries {idempotency_key, input} with the retry rule that the same key and input should be reused. That adds operational meaning the schema alone does not convey.

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 opens with a specific verb and resource set: 'Execute a model, API, or Agent Service.' It immediately disambiguates the execution modes (sync models vs async image/video/audio jobs vs Services) and points to the sibling that handles retrieval, so an agent can distinguish sandbase_run from sandbase_run_get without opening either schema.

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?

It gives clear branching guidance: sync returns directly, async must be polled via sandbase_run_get, Services require an idempotency key and also require polling with service_id and run_id. What's absent is guidance on prerequisites for calling at all (e.g., inspect the schema first via sandbase_inspect, or when to prefer sandbase_discover), so the when-to-use context is strong but not exhaustive.

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.