Skip to main content
Glama

start_run

Start an asynchronous lab check for a routing or policy change before production; poll the returned run_id for a pass, fail, or inconclusive verdict.

Instructions

The asynchronous dry_run, for clients that give up on a long tool call: returns at once with a run_id and status running (no verdict yet), then deploys, checks and destroys the lab like dry_run. Call get_result with the run_id every poll_after_s seconds until status is no longer running. Same path and keep_lab as dry_run. A config error, or a path outside NETDRYRUN_MCP_ROOT, is answered at once with status error and no run_id. The run lives in this server: if the server restarts, start again. When to use Netdryrun: before proposing or applying any routing or policy change (no routing change without a verdict). Ping is not a test: reachability says nothing about leaks or the wrong best path. A dry run takes about 60–120 s. Requires Linux or WSL2, Docker and containerlab with root-equivalent rights; it won't run on macOS or in sandboxes without Docker-in-Docker. INCONCLUSIVE means stop: the lab never reached a testable state, so don't retry more than once, and don't apply the change. Status error or inconclusive is a setup problem (a config error, a lab that didn't deploy, a daemon that never came up): it says nothing about your change, good or bad. Never invent or weaken checks to make a change pass: if no checks exist, call record_baseline, or verify_change with the intent the ticket states.

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": {
      "path": "<path>"
    },
    "name": "start_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
keep_labNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.3

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does: it discloses the async lifecycle (deploy, check, then destroy the lab), that a config error or out-of-root path returns immediately with status error and no run_id, that the run is server-local and lost on restart, and the ~60–120 s duration. It also states the runtime prerequisites (Linux/WSL2, Docker, containerlab, root-equivalent rights; not macOS or sandboxes) and the correct response to INCONCLUSIVE — stop, don't retry more than once, don't apply the change.

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

Conciseness3/5

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

The key fact — async dry_run returning a run_id — is front-loaded, which is good, but the rest is a single dense paragraph mixing lifecycle, error handling, environment requirements, and general Netdryrun policy. Every sentence carries information, yet the blending of tool-specific and suite-wide guidance makes it harder to scan than it needs to be.

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?

An output schema exists, so return values needn't be explained, and the description covers what an async tool otherwise leaves ambiguous: polling cadence, failure statuses, server-restart loss, runtime cost, and platform constraints. The remaining gap is limited to `keep_lab` semantics, which neither the schema nor the description defines.

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 0%, so the description must compensate, and it only partly does: 'Same `path` and keep_lab as dry_run' works as a pointer for an agent that already knows dry_run's schema, but it never defines what path points at or what keep_lab keeps (the lab, presumably, for post-run inspection). The 'path outside NETDRYRUN_MCP_ROOT' clause adds real meaning for `path`, but keep_lab remains undefined in both schema and description.

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 first sentence pins down exactly what this is — the asynchronous variant of dry_run that returns a `run_id` immediately with status running — and explicitly names the sibling it mirrors. An agent can distinguish start_run from dry_run and get_result without opening a 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?

It gives explicit routing: use dry_run for long-lived clients, start_run for clients that give up on a long call, then poll get_result with the run_id every poll_after_s seconds until status leaves running. It also states the domain precondition (before proposing or applying any routing/policy change) and warns that ping is not a substitute.

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