BCD — Bridge Control Delegate

start_process

Destructive

Start a long-running or interactive command in the background (dev servers, long builds, REPLs, anything over 2 minutes) and return its session id as JSON. timeoutMs or waitForPrompt also waits for first output. Then process_output reads it, process_input types into it and stop_process stops it. The process keeps running past timeouts and reconnects.

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": {
      "command": "<command>"
    },
    "name": "start_process"
  }
}

Input Schema

Name	Required	Description	Default
`cwd`	No
`command`	Yes
`deviceId`	No	Computer name or id from list_devices. Optional with one computer online or a default set.
`priority`	No	Scheduling priority. Use "low" for heavy or long-running work such as builds, training or test suites.	normal
`timeoutMs`	No
`waitForPrompt`	No
`workSessionId`	No	Work session from create_work_session. Pass the same ID on every call in this conversation; omit for legacy unscoped work.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 30, 2026

removedInput schema / properties / cwd / default
```
Removed value: -"~"
```

addedInput schema / properties / workSessionId

Added value: +{
+  "description": "Work session from create_work_session. Pass the same ID on every call in this conversation; omit for legacy unscoped work.",
+  "format": "uuid",
+  "type": "string"
+}

First observedSep 30, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare destructive/openWorld/non-readOnly, so the bar is lower; the description adds genuinely new behavioral context by stating the process keeps running past timeouts and reconnects, and that timeoutMs/waitForPrompt wait for first output. It does not explain the destructive implication (what stop_process destroys or resource impact), leaving one gap.

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?

Three sentences, front-loaded with the core purpose and the return value, then the lifecycle and durability note. No filler, though the follow-up-tool sentence could be tighter.

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 7-param tool with no output schema, the description states the return value (session id as JSON), the waiting semantics, and the durability/reconnect behavior an agent must know. It still omits the destructive consequence and a few parameter meanings, so it is not fully complete.

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 43%, below the 50% threshold, so the description must compensate. It clarifies the behavior of timeoutMs and waitForPrompt (waits for first output) but says nothing about cwd, command semantics, or how they interact, leaving half the parameters undocumented in both places.

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?

States a specific verb+resource (start a long-running/interactive command in the background) and gives concrete examples (dev servers, builds, REPLs, anything over 2 minutes). The 2-minute threshold implicitly distinguishes it from run_command, but it never names that sibling explicitly, so the differentiation is inferred rather than stated.

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?

Gives clear usage context (long-running, interactive, over 2 minutes) and maps out the lifecycle with the correct follow-up tools: process_output reads, process_input types, stop_process stops. It does not explicitly route short commands to run_command, so the alternative is only implied by the duration threshold.

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

All BCD — Bridge Control Delegate tools Inspect

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

Need Help?