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

io.github.chowdhurylab-studio/ipro-agent

ipro_run

Launch a detached protein design run and get a run ID immediately; poll status instead of waiting. Set max_minutes for unattended runs and avoid launching impossible designs without PyMOL.

Instructions

Launch a design run and return immediately with a run id. The run is DETACHED and can take minutes to days, so poll ipro_status rather than waiting. Refuses to launch when a design is impossible (no PyMOL). Always pass max_minutes for an unattended run.

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": {
      "spec": "<spec>"
    },
    "name": "ipro_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNooverride loop.random_seed
specYesPath to a spec YAML/JSON file, OR the spec's YAML content inline. Inline content is written to a temporary file first. Relative molecule paths inside a spec resolve against the spec file's own directory, so inline specs must use absolute structure paths.
run_dirNooutput directory; must be empty or new
iterationsNooverride loop.iterations
max_minutesNowall-clock budget; stops cleanly at a checkpoint

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, the description carries the full burden and discloses the critical async behavior: detached execution, immediate return with a run id, and a duration range of minutes to days. It also discloses a refusal condition, though it does not cover permissions, concurrency limits, or what happens to a partially written run_dir on failure.

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 what the tool does and how it returns. The polling alternative and the max_minutes recommendation each earn their place with no filler.

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?

No output schema exists, yet the description explains the return value (run id) and the polling model, which is the key thing an agent needs. It is nearly complete for this tool's complexity, with only minor gaps around failure modes and run_dir handling.

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%, so the baseline is 3. The description still adds actionable meaning beyond the schema by recommending max_minutes for unattended runs, which is a practical constraint the parameter definition alone does not convey.

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 and resource (launch a design run) and immediately defines the return contract: it returns a run id and is detached. This clearly distinguishes it from ipro_status, which the description names as the polling counterpart.

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?

Explicitly says to poll ipro_status rather than wait, since runs can take minutes to days, and states the precondition under which it refuses to launch (no PyMOL). It also gives a usage instruction to always pass max_minutes for unattended runs.

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