Skip to main content
Glama

exec_in_service

Runs a one-off command inside a hosted service's environment, using the same code, environment, database, and /data, and returns its output.

Instructions

Servisin ortamında (aynı kod, env, veritabanı, /data) tek seferlik bir komut çalıştırır ve çıktısını döner — ör. 'python manage.py migrate', 'node scripts/seed.js', 'ls -la /data'. En fazla 300 sn; çıktı en fazla 64 KB.

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": {
      "serviceId": "<serviceId>",
      "cmd": "<cmd>"
    },
    "name": "exec_in_service"
  }
}

Input Schema

NameRequiredDescriptionDefault
cmdYes
serviceIdYesServis id (list_services / create_service yanıtındaki id)
timeoutSecNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the important facts that the command shares the live code, env, database, and /data mount, meaning side effects hit real state, plus a 300-second limit and 64 KB output cap. However it omits execution semantics an agent needs for a high-risk tool: blocking vs async, shell interpretation, exit-code/error reporting, concurrency behavior, and what happens on timeout.

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?

One compact sentence plus examples and hard limits; the environment scope is front-loaded and every clause adds information. Nothing is redundant or padded.

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 remote-execution tool with no annotations and no output schema, the description covers the essentials: execution environment, side-effect surface, time budget, and output size. Remaining gaps (exit status, truncation behavior, preconditions) are meaningful but secondary.

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 only 33% (only serviceId is documented), so the description must compensate. It partly does: the examples clarify what kind of string cmd accepts (shell commands such as migrations, seed scripts, ls) and the 300-second ceiling explains timeoutSec's upper bound. Nothing is said about the 1000-character cmd limit, shell quoting, or what timeoutSec's default is when omitted.

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 and resource: runs a one-off command inside the service's runtime environment (same code, env, database, /data) and returns its output. The concrete examples ('python manage.py migrate', 'ls -la /data') make the capability unambiguous. It does not explicitly contrast itself with siblings such as restart_service or get_service_logs, so it falls just short of a 5.

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

Usage Guidelines3/5

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

Usage is only implied through examples of one-off maintenance/seed/inspection commands. There is no explicit statement of when to prefer this over deploy_service, restart_service, or reading get_service_logs, nor any precondition such as whether the service must be running or whether this blocks on the live instance.

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