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

io.github.chowdhurylab-studio/ipro-agent

ipro_result

Retrieves a completed design run's mutation string, sequence, score change, components, notes, alternatives, and optional PDB coordinates so MCP clients can report results and hand over structures.

Instructions

The design a run produced: the mutation string, the sequence, the score change, the components, the notes, the ensemble of alternatives, and -- with include_structure -- the designed PDB itself. Report from this rather than from ipro_status alone: an MCP client has no shell, so this is the only way to hand over the coordinates. If no mutation was kept it says so, and the structure is then the starting point.

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_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNoor the id ipro_run returned
run_dirNothe run directory
include_structureNoinclude the designed PDB as text (about 200 KB for a 340-residue chain); off by default

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, the description carries the full burden, and it does disclose the important behavior: include_structure yields the designed PDB text and defaults off, and a run with no kept mutation is signaled rather than silently returning nothing. It omits prerequisites — whether the run must be complete, what happens with an unknown or in-progress run_id, and any cost of pulling ~200 KB of coordinates — which matters for a payload-heavy read.

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 sentences, front-loaded with the returned content, then the sibling-routing rationale, then the edge case. Every sentence carries information, though the first is a long comma-separated enumeration that could be tightened into a clearer list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter read tool with no output schema, the description does well by enumerating the returned fields and the include_structure payload, since there is no output schema to explain returns. It is incomplete on the run_id/run_dir selection and on failure/prerequisite behavior, which an agent needs to call it correctly on the first try.

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 100%, so all three parameters are documented there, giving a baseline of 3. The description reinforces include_structure's effect and size but adds nothing on run_id versus run_dir — the key ambiguity, since zero parameters are required and an agent gets no hint about which identifier form to supply or whether they can be combined.

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 makes clear this returns the results of a finished run — mutation string, sequence, score change, components, notes, alternatives, and optionally the PDB — so an agent knows exactly what resource it gets. It also distinguishes itself from ipro_status by naming that sibling. It stops short of a crisp verb phrase like 'Retrieve the results of a run', but the intent is unambiguous.

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?

Explicit routing guidance: 'Report from this rather than from ipro_status alone', with the rationale (an MCP client has no shell, so this is the only way to hand over coordinates). It also tells the agent the no-mutation case is reported explicitly. It does not say when this tool is inappropriate (e.g. while a run is still in progress) or point at ipro_iterations/ipro_score as alternatives.

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