Skip to main content
Glama
rcsb

io.github.rcsb/rcsb-mcp

Official
by rcsb

rcsb_describe_data_object

Read-onlyIdempotent

Discover available fields for any RCSB Data API object. Get verified dotted paths to use directly in fields= arguments.

Instructions

Discover the fields available on a Data API object, from the live GraphQL schema.

Use this to find exactly what to request in a rcsb_get_* tool's fields= argument. The rcsb_get_* default selections are compact summaries, but the underlying GraphQL types have far more (e.g. CoreEntry has ~100 fields). Every path it returns is verified against the live schema, so it is safe to pass to fields= directly.

Two ways to use it, both returning dotted paths ready for fields=:

  • BROWSE a level (default, max_depth=1): list one object's own fields, then drill into a nested one with into. Workflow: rcsb_describe_data_object("entries") -> spot a nested object such as "rcsb_entry_info" -> rcsb_describe_data_object("entries", into="rcsb_entry_info") to list its leaves.

  • SEARCH by keyword: raise max_depth (e.g. 3) and pass query to flatten the object's whole tree — including nested and cross-object paths like "pubmed.rcsb_pubmed_abstract_text" — and keep only matching fields. Combine them: into scopes the walk, so into="rcsb_polymer_entity", max_depth=2 searches just that sub-tree (cheaper and more focused than flattening from the root).

Each returned field has:

  • path: dotted path from the object root, ready to use in fields=

  • kind: "scalar" (a leaf you can select directly) or "object" (drill in, or select with a sub-selection)

  • type: the field's GraphQL type name

  • list: whether the field returns a list

  • description: schema description, when present

Args: object_key: Which object to describe — the key matching the rcsb_get_* tool. into: Optional dot-path of nested object field(s) to scope to, e.g. "rcsb_entry_info" or "polymer_entities.rcsb_polymer_entity". query: Optional case-insensitive keyword, matched against each field's path (relative to the scope) and its description, e.g. "resolution", "abstract", "organism". max_depth: How many levels to walk (1-6, default 1 = this level only). Depth 2 reaches e.g. "pubmed.rcsb_pubmed_abstract_text"; depth 3 reaches "polymer_entities.rcsb_polymer_entity.pdbx_description". Deeper is slower on a cold cache; prefer a query (and into) over a broad deep walk.

Returns: {object_key, graphql_type, path, query, max_depth, field_count, fields:[{path, kind, type, list, description}], truncated?, note?}. When the result set is capped, truncated is true and note explains how to narrow it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intoNo
queryNo
max_depthNo
object_keyYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

Annotations already indicate readOnly and idempotent hints, but the description adds valuable behavior: fields are verified against the live schema, depth limits, caching performance caveats, truncation behavior, and how narrowing works. No contradiction with annotations.

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?

Although long, the description is tightly structured: clear summary, usage modes, parameter explanations, and return format. Every sentence adds value, no fluff, and it's front-loaded with the core purpose.

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 discovery tool with rich output schema, the description covers all necessary context: return structure (with field names and types), usage patterns, limitations (truncation, depth), and integration with sibling tools. Complete and self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description fully compensates by explaining every parameter: object_key (which object), into (nested path), query (case-insensitive keyword matching), and max_depth (with examples for depths 1-3). Provides concrete examples for each.

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 description opens with a specific verb+resource: 'Discover the fields available on a Data API object, from the live GraphQL schema.' It clearly distinguishes itself from sibling rcsb_get_* tools by explaining it provides the fields to request in those tools, with no ambiguity.

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 when to use: 'Use this to find exactly what to request in a rcsb_get_* tool's fields= argument.' It contrasts with default selections and provides two detailed usage modes (browse and search by keyword) with workflow examples, effectively guiding tool selection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rcsb/rcsb-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server