Skip to main content
Glama

Show a protein or antibody

generate_protein_or_antibody
Idempotent

Draw a protein, enzyme, or antibody as a cartoon ribbon diagram by fetching its PDB or AlphaFold structure and saving PNG/SVG files with a rotatable 3D panel.

Instructions

Draw a protein, enzyme or antibody as a cartoon (ribbon diagram).

Fetches its structure from the PDB (AlphaFold model if there is none) and writes PNG/SVG files plus a rotatable panel: helices as spirals, strands as arrows, bound groups such as heme or zinc as sticks. Works for enzyme and protein names (lysozyme, trypsin, hemoglobin, insulin), gene symbols (RecA), antibody INNs (trastuzumab) and a plain "antibody" or "IgG". Antibodies come with the IgG domain scheme; an antibody without a known structure shows the architecture of an intact IgG. A protein's 3D structure is this tool too — the panel rotates.

Not this tool for: a small molecule, a peptide sequence or any skeletal formula (use generate_molecule); a small molecule as a 3D model (use generate_3d); a protein's function, EC number or cofactors as text (use lookup, topic "biochem").

Args: name: English protein, enzyme, gene or antibody name ("lysozyme", "trastuzumab", "antibody"); an organism may follow ("human lysozyme"). formats: "png", "svg" (default both). A cartoon has no CDXML.

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": {
      "name": "<name>"
    },
    "name": "generate_protein_or_antibody"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
formatsNo

Output Schema

NameRequiredDescriptionDefault
svgNo
nameNo
typeNoprotein
atomsNo
filesNo
viewsNo
foundAsNo
messageNo
proteinNo
viewSvgNo
lipinskiNo
subtitleNo
viewAtomsNo
candidatesNo
cdxml_pathNo
propertiesNo
stereoNoteNo
initialViewNo
viewRequestNo
projectionNoteNo
stereoWarningsNo
functionalGroupsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.10.0

TDQS

A4.7/5.0
Behavior4/5

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

Beyond the openWorldHint annotation, the description discloses where data comes from (PDB, with AlphaFold fallback when no structure exists), what artifacts are produced (PNG/SVG files plus a rotatable panel), and how a structureless antibody is handled. It does not mention failure modes or timing/rate limits for the remote fetch, so it stops short of a 5.

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?

Front-loaded one-line summary, then data-source and rendering details, then a clearly labeled exclusion list, then an Args block. Every sentence contributes (input forms, antibody handling, sibling routing), with no filler.

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

Completeness5/5

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

For a two-parameter generative tool with an output schema, the description covers input forms, rendering behavior, remote data source and fallback, output artifacts, and sibling boundaries. Nothing an agent needs in order to choose and invoke it correctly is missing.

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 description coverage is 0%, so the description carries the parameter burden and mostly succeeds: it enumerates accepted name forms (protein/enzyme name, gene symbol, antibody INN, generic 'antibody', optional organism suffix) and constrains formats to png/svg with a stated default. The stated default 'both' is slightly at odds with the schema's null default, leaving minor ambiguity.

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?

The first line gives a concrete verb and resource ('Draw a protein, enzyme or antibody as a cartoon (ribbon diagram)'), and the body spells out scope in terms of accepted inputs and rendered features (helices, strands, bound groups). It is unmistakably distinct from generate_molecule and generate_3d, which it names.

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?

There is an explicit 'Not this tool for' block that routes small molecules to generate_molecule, 3D small-molecule models to generate_3d, and textual function/EC/cofactor questions to lookup with a topic hint. Positive-use conditions are also given (protein names, gene symbols, antibody INNs, plain 'antibody').

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