Skip to main content
Glama
io.github.chowdhurylab-studio/ipro-agent

io.github.chowdhurylab-studio/ipro-agent

ipro_setup

Check whether this machine can run a protein design and, with confirm=true, install missing dependencies such as conda-only PyMOL; without confirm, only report the install plan.

Instructions

Check whether this machine can actually run a design and, with confirm=true, install what is missing. Call it when ipro_doctor reports can_design=false. PyMOL is conda-only and has no fallback, so pip cannot fix it. Installs nothing without confirm=true; tell the user what it will do first.

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": "ipro_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNofalse (default) reports the plan; true runs the conda install, which downloads ~500 MB and changes the machine

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses the default dry-run behavior, that confirm=true mutates the machine, the conda-only dependency constraint, and the instruction to inform the user first. It stops short of stating whether elevated privileges or network access are required, how failures surface, or whether repeated runs are idempotent.

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?

Four short sentences, front-loaded with the core action and followed by the trigger, the constraint, and the safety instruction. No sentence is redundant with another.

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 one-parameter, no-output-schema tool with no annotations, this covers the trigger, the safety default, and the dependency constraint an agent needs before calling it. The one gap is what the confirm=false plan output looks like, which matters since the agent is told to relay it to the user first.

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

Parameters4/5

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

Schema coverage is 100% and the single parameter is already well documented, so the baseline is 3. The description still adds value by framing the two modes as report-the-plan versus run-the-install and by tying the confirm=true path to a user-notification obligation.

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?

States a specific verb pair and resource: check whether the machine can run a design, and with confirm=true install what is missing. It is clearly differentiated from the sibling ipro_doctor, which is named as the diagnostic that triggers this tool rather than a duplicate of it.

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?

Gives an explicit trigger condition ('Call it when ipro_doctor reports can_design=false') and an explicit guardrail ('Installs nothing without confirm=true; tell the user what it will do first'). It also rules out an alternative remedy by noting PyMOL is conda-only and pip cannot fix it.

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