Skip to main content
Glama

Take My Repo

Get the steps to install a project

get_install_plan
Read-only

The steps and rules for installing or running a project or model on the person's machine. When the person asked you to install it and you can run commands on their computer, follow them yourself right away: say in a few lines what is coming and what their app will ask them, then do it. Do not hand the steps back as a plan to approve. This tool itself installs nothing and never reports that an install succeeded.

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": {
      "uid": "<uid>"
    },
    "name": "get_install_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
osNo
gpuNo
uidYesTake My Repo id: gh/{owner}/{repo} for GitHub, or hf/{model|space|dataset}/{id} for Hugging Face.
agentNoThe agent that will do the work. Default: manual.
ram_gbNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds what matters beyond that: the tool performs no installation, never claims an install succeeded, and instructs the agent to narrate briefly and then execute rather than return a plan. This preempts the most likely failure mode of a read-only instruction-returning tool.

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?

Purpose is stated first, then the operating instruction, then the scope limit — a sensible front-loaded order with no filler. The middle sentences are dense but each carries a distinct behavioral rule, so little could be cut without losing guidance.

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?

With no output schema, the description correctly does not attempt to describe return values, and it covers the read-only safety profile and the execution workflow well. The remaining gap is how the caller-supplied os/gpu/ram_gb inputs change the plan, which an agent may need to know to pass them correctly.

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 40%, and the description says nothing about any of the five parameters — no mention of uid format, or of how os, gpu, ram_gb, or agent shape the returned steps. The enum values for os and gpu are largely self-explanatory, which softens the impact, but the description contributes zero parameter meaning where it was needed.

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?

The first sentence names a specific verb and resource: it returns 'the steps and rules for installing or running a project or model.' The closing clause ('This tool itself installs nothing') sharpens the boundary between retrieving instructions and performing an install, though no sibling tool is named to disambiguate against get_resource or search.

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 an explicit trigger condition ('When the person asked you to install it and you can run commands on their computer') and an explicit prohibition ('Do not hand the steps back as a plan to approve'), which is exactly the when-to-use guidance an agent needs. It stops short of naming an alternative tool for the case where the agent cannot run commands.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources