CinderRoute Agent Exchange

ci_run_build_command

Destructive

Execute a diagnostic command on an isolated CI runner and return bounded stdout and stderr for build troubleshooting. Pass the build_id returned by the incident tools to keep the investigation linked.

Input Schema

TableJSON Schema

Name	Required	Default
`shell`	No	bash
`command`	Yes
`build_id`	Yes
`runner_id`	No
`timeout_seconds`	No
`working_directory`	No	/workspace/api-gateway

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`stderr`	No
`stdout`	No
`build_id`	Yes
`exit_code`	Yes
`observed_at`	Yes
`execution_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 10, 2026

changedInput schema / required

Previous value: -[
-  "command"
-]New value: +[
+  "build_id",
+  "command"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "build_id": {
+      "type": "string"
+    },
+    "execution_id": {
+      "type": "string"
+    },
+    "exit_code": {
+      "type": "integer"
+    },
+    "observed_at": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "status": {
+      "type": "string"
+    },
+    "stderr": {
+      "type": "string"
+    },
+    "stdout": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "execution_id",
+    "build_id",
+    "status",
+    "exit_code",
+    "observed_at"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedSep 10, 2026
- addedInput schema / properties / build_id
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / runner_id
```
Added value: +{
+  "type": "string"
+}
```
First observedSep 10, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With destructiveHint=true already carrying the destructive warning, the description adds useful behavioral context: the runner is isolated and stdout/stderr are bounded. This tells the agent that output is capped and that execution is meant to be separate from production systems.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with action and purpose, with no filler. The second sentence adds a practical linking hint without repetition.

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

Completeness2/5

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

The tool has six parameters, no schema descriptions, and a destructive annotation; the description leaves parameter meaning and usage boundaries mostly implicit. It relies heavily on parameter names and output schema, making it incomplete for an arbitrary-command execution tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only relates to build_id ('Pass the build_id') and command generically ('Execute a diagnostic command'); shell, runner_id, working_directory, and timeout_seconds are not addressed at all.

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 ('Execute a diagnostic command on an isolated CI runner') and states its purpose ('for build troubleshooting'). This clearly separates it from read-only siblings like ci_read_build_logs and from state-changing ones like ci_retry_build.

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 context: use for build troubleshooting and pass the incident-related build_id to keep the investigation linked. It does not explicitly name alternatives or exclusions, but the troubleshooting framing plus 'isolated CI runner' makes the intended context clear.

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

All CinderRoute Agent Exchange 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?