folio-mcp

find_connections

Retrieve explicit subject-property-object links from a FOLIO concept to see recorded relationships, with optional property and object filters.

Instructions

Find explicit property links (subject -> property -> object triples) from a FOLIO concept, e.g. Actor / Player -folio:drafted-> Document / Artifact.

FOLIO records only a small number of these links (mostly on top-level classes), so most concepts have none. For broader/narrower relationships use get_parents/get_children; for related concepts see "see_also" in get_concept.

Args: subject_iri: IRI or short ID of the subject concept (branch names accepted). property_name: Optional property label (e.g. "folio:drafted") or IRI. object_iri: Optional object concept IRI to filter by.

Returns: JSON array of {subject, property, object} (each {iri, label}), or {results: [], note} when the concept has no recorded links.

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": {
      "subject_iri": "<subject_iri>"
    },
    "name": "find_connections"
  }
}

Input Schema

Name	Required	Description	Default
`object_iri`	No
`subject_iri`	Yes
`property_name`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.1Aug 1, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the sparse-data behavior and the empty-result shape ({results: [], note}), which is the key behavioral surprise for this tool. It does not discuss permissions or rate limits, but for a read-only lookup tool that gap is minor.

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?

The core purpose and caveat are front-loaded, followed by cleanly separated Args and Returns blocks. The Returns block partially duplicates the existing output schema, which is minor waste but keeps the definition self-contained.

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 3-parameter read lookup, the definition covers scope, alternatives, parameter meaning, and the empty-result case. Since an output schema already exists, the Returns section is slightly redundant, but nothing essential 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 coverage is 0%, so the description must compensate, and it does: subject_iri accepts an IRI, short ID, or branch name; property_name accepts a label like "folio:drafted" or an IRI; object_iri is an optional filter. These are real semantics absent from the schema, though the exact ID formats are only loosely specified.

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 states a specific verb and resource: finding explicit subject->property->object triples from a FOLIO concept, with a concrete example (Actor/Player -folio:drafted-> Document/Artifact). It also explicitly distinguishes itself from get_parents/get_children and from the see_also field in get_concept, so an agent can pick it apart from siblings without opening schemas.

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?

It gives explicit when-to-use (explicit property links), a strong when-not/expectation caveat ("FOLIO records only a small number of these links... most concepts have none"), and names the alternatives for other relationship types (get_parents/get_children for broader/narrower, get_concept for see_also).

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

Deploy Server