Skip to main content
Glama

start_backend

Starts or keeps the shared backend running ahead of a batch and sets an idle timeout so it stays available long enough without remaining up indefinitely.

Instructions

Start (or keep) the shared backend ahead of a batch.

idle_timeout_seconds: how long the backend stays up after the last activity. If this call starts the backend the value is used as is; if it is already running, a longer value extends it and a shorter one is ignored (the effective value is the maximum requested since it started). Bounded to the configured min and max (default 60 to 7200 s). Returns the effective value.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_backend"
  }
}

Input Schema

NameRequiredDescriptionDefault
idle_timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses that the call is keep-alive rather than strictly start, that shorter timeouts are silently ignored, and that the effective value is the max requested since start. It omits whether the call blocks until the backend is ready, permission requirements, and failure behavior.

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?

Front-loads the one-line purpose, then a labeled block for the single parameter, which is easy to scan. The parenthetical "(the effective value is the maximum requested since it started)" is slightly convoluted but genuinely load-bearing.

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?

There is no output schema, and the description correctly states the return value ("Returns the effective value"), which is the key thing an agent needs to continue. For a one-optional-parameter lifecycle tool this is nearly complete, with only readiness/blocking and error semantics missing.

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

Parameters5/5

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

Schema coverage is 0% – the schema only declares an optional nullable integer with a null default. The description fully compensates by defining what the value means, how it interacts with an already-running backend (extend vs. ignore), and the configured default bounds of 60–7200 seconds.

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 combination ("Start (or keep) the shared backend") and adds the operational intent ("ahead of a batch"). An agent can distinguish it from stop_backend without opening either schema, though the description never names the inverse sibling explicitly.

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?

"Ahead of a batch" gives a clear trigger condition for calling this tool, implying it's used to avoid cold-start latency before a multi-step job. There are no explicit exclusions or named alternatives, so it stops short of a 5.

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