Jean — Molecular Biology & Genomics

read_structure

Read-only

Read a structure file — PDB, PDBx/mmCIF, or a core CIF small-molecule crystal structure — and report what is in it: the chains and what kind each is, their sequences, the ligands and ordered solvent, the disulfides, the residues the depositor declared modified, the temperature-factor range, the unit cell and space group, the resolution and the experiment.

Input Schema

Name	Required	Description
`text`	Yes	the coordinate file's contents — a PDB flat file, a PDBx/mmCIF, or a core CIF; the format is read from the bytes, not from a name, because .cif is shared by two unrelated dictionaries.
`model`	No	which model of an ensemble to describe, 1-based. An NMR entry holds many complete conformers and they are alternatives rather than parts, so the counts always describe ONE of them. The upper bound is the FILE's, so it is not declared here — an out-of-range model is refused by name, with the range that exists.
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.

Output Schema

Name	Required	Description
`id`	Yes	the 4-character entry id the file declares about itself, empty when it declares none
`cell`	Yes	unit cell and space group, absent for a determination with no crystal
`atoms`	Yes	atoms in the model described
`title`	Yes	the entry's own title line
`chains`	Yes	one row per chain: id, polymer kind, residue and atom counts, the author numbering range, and the observed one-letter sequence
`extent`	Yes	the longest side of the bounding box in angstroms — whether this will fit a pore, a groove or a box
`format`	Yes	which reader actually ran: `pdb`, `mmcif`, or `smallcif` for a core CIF (small-molecule crystallography, which shares the .cif extension with mmCIF and is a different dictionary)
`method`	Yes	the experimental technique(s) — genuinely more than one for a neutron/X-ray structure
`models`	Yes	conformers in the file; more than one means an ensemble
`waters`	Yes	ordered solvent molecules, counted separately from ligands
`bFactor`	Yes	min, max and mean isotropic B over every atom, or null when the file states none
`dialect`	Yes	the same answer in words, for a reply to quote
`formula`	Yes	the empirical formula the file STATES about itself (`_chemical_formula_sum`), empty when it states none. For a crystal structure it describes the contents of the CELL, so it can name more atoms than the sites listed
`helices`	Yes	helices the DEPOSITOR annotated (not a calculation over the coordinates)
`ligands`	Yes	non-water heteroatom components with how many copies of each — the ions, cofactors and bound compounds
`strands`	Yes	strands the depositor annotated
`modified`	Yes	modified residues with the standard residue each stands in for, from the file's own MODRES / _pdbx_struct_mod_residue — the only authoritative source for what a component like MSE IS
`residues`	Yes	residues in the model described, solvent included
`warnings`	Yes	lines the reader could not parse, named rather than dropped
`sequences`	Yes	the CONSTRUCT sequence per chain as the file declares it (SEQRES / _entity_poly), which includes residues that were never resolved
`disulfides`	Yes	disulfide bonds the file annotates
`hasPolymer`	Yes	whether any chain is a polymer. False for a core CIF and for a coordinate set holding only a ligand — where `chains`, `residues` and `sequences` describe a wrapper rather than a molecule, and `atoms` is a count of symmetry-independent SITES
`resolution`	Yes	diffraction limit in angstroms. 0 means the entry states NONE (an NMR determination has no resolution) — read `hasResolution` rather than treating 0 as sub-angstrom
`hasResolution`	Yes	whether the entry states a resolution at all

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 25, 2026
- addedOutput schema / properties / extent / x-unit
```
Added value: +"Å"
```
- addedOutput schema / properties / resolution / x-unit
```
Added value: +"Å"
```
First observedOct 20, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description does add real behavioral detail — format is sniffed from bytes rather than filename, and out-of-range models are refused by name with the valid range — but it says nothing about cost on large files or how partial/truncated structures are handled.

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?

A single front-loaded sentence with no filler, opening on the verb and the accepted formats before the output inventory. The long clause listing report contents is somewhat redundant against the output schema, but it is ordered and readable rather than padded.

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 read-only parser with a full-coverage schema, an output schema, and clear annotations, the definition covers inputs, format ambiguity, and the model-selection error path. The only material gap is the absent comparison to read_structure_consensus, which leaves sibling routing to inference.

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, and the description's statement that reported counts always describe ONE model of an ensemble gives the `model` parameter meaning the schema description only partly conveys. It still adds nothing about `_subject` or `_files`, but with full schema coverage that is acceptable.

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 ('Read a structure file') and then explicitly bounds the accepted formats (PDB, PDBx/mmCIF, core CIF small-molecule), which separates it from generic record readers. The enumerated report contents (chains, sequences, ligands, disulfides, B-factor range, unit cell, space group, resolution, experiment) make the scope unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: it is the tool that describes a coordinate file. No sentence says when to prefer it over the sibling read_structure_consensus, nor whether it is appropriate for large ensembles where only one model is described. An agent must infer the routing from the tool name alone.

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

All Jean — Molecular Biology & Genomics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?