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

io.github.chowdhurylab-studio/ipro-agent

ipro_iterations

Retrieve per-iteration scores, acceptance status, and rejection reasons from a protein design run trajectory without reading the unbounded iterations.jsonl file directly.

Instructions

The tail of the trajectory: per-iteration score, whether it was accepted, and why it was rejected. The reporting rule tells you to read the per-iteration reasons, and this is how. Never read iterations.jsonl directly; it grows without limit.

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_iterations"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNohow many of the most recent to return (default 20, max 200)
run_idNoor the id ipro_run returned
run_dirNothe run directory
only_acceptedNoonly the iterations that were accepted

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden and does cover two useful traits: the artifact is unbounded so direct file reads are unsafe, and the default/max windowing is surfaced. It does not state that this is a read-only, side-effect-free operation, nor how results are ordered or what a record looks like beyond the three named fields.

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?

Three short sentences, front-loaded with the payload description, then the routing justification, then the prohibition. The clause about the reporting rule is slightly meta but does earn its place as the reason this tool exists; nothing else is padding.

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, so the description must indicate return shape, and it names the three key fields plus the recency window. All four parameters are documented and the read path is made safe against the raw file; only ordering, pagination beyond the limit, and the read-only nature are left implicit.

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 description coverage is 100%, so every parameter (limit, run_id, run_dir, only_accepted) is already documented in the schema, including the default-20/max-200 bounds. The description adds only the conceptual framing of a 'tail' of recent iterations and nothing new about parameter meaning or interaction, which is the expected baseline when the schema does the work.

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 description identifies the specific resource ('the tail of the trajectory') and enumerates what each record yields: per-iteration score, acceptance status, and rejection reason. It is clearly distinct from a whole-run summary tool, though it never names a sibling tool that would be the alternative, only the raw file iterations.jsonl.

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 states the condition that selects it (the reporting rule requires per-iteration reasons) and explicitly excludes the tempting alternative of reading iterations.jsonl directly, citing unbounded growth. It stops short of saying when to prefer ipro_result or ipro_score for whole-run aggregates, so differentiation against siblings is incomplete.

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