Skip to main content
Glama
Sign In

OTP

by io.github.david-steel
OverviewDiscussionsAdmin

Run a process now

run_process
Destructive

Run a process once, right now, instead of waiting for its schedule. The run spends the organization's wallet. Use this when someone wants the result immediately, or wants to see what a process produces before committing it to a schedule -- running it once first is usually the better order. Call list_processes for the exact agent externalId and SOP title.

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_external_id": "<agent_external_id>",
      "sop_title": "<sop_title>"
    },
    "name": "run_process"
  }
}

Input Schema

NameRequiredDescriptionDefault
sop_idNoSOP id when list_processes returned one
sop_titleYesExact SOP title, from list_processes
agent_external_idYesThe seat that owns the process, from list_processes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description adds the crucial non-schema fact that the run spends the organization's wallet. It stops short of explaining reversibility, concurrency behavior, or whether the run is synchronous, so it is strong but not complete.

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 each sentence carries real information (immediacy, cost, use case, prerequisite lookup). Slightly conversational, but no filler sentences.

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?

No output schema exists, and the description never says what a run returns or how to observe its result (run id, async status, where output appears). For a mutating, cost-incurring action, that is a meaningful gap even though the cost warning and prerequisite are well covered.

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 the schema descriptions already say each parameter comes 'from list_processes.' The description's pointer to list_processes repeats that provenance rather than adding new syntax or format guidance, so the baseline 3 applies.

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?

Opens with a specific verb and resource ('Run a process once, right now') and distinguishes immediate execution from scheduled execution, which separates it from create_schedule/update_schedule siblings. An agent can identify the tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it ('someone wants the result immediately,' preview before scheduling) and even gives an ordering recommendation ('running it once first is usually the better order'). It also routes the agent to list_processes for the required identifiers, covering prerequisites.

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

All OTP 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