Skip to main content
Glama

reference_references

Read-only

Read bounded incoming or outgoing typed cross-reference edges for an X++ artifact or member to inspect dependencies, extensions, and metadata links; reindex if results are empty.

Instructions

Read bounded incoming or outgoing typed reference edges for an artifact or member, from the IDE's cross-reference store. An artifact id (/Tables/CustTable) covers every nested member (fields, methods, field groups, form data sources and controls...), its extensions (CustTable.) and metadata links such as menu item -> form, security privilege -> menu item, query/entity/form field bindings and EDT relations (provider ide-xref-metadata, paths dynamics://Type/Name/...?Property). A member id (/Tables/CustTable/Fields/AccountNum, /Forms/F/DataSources/D/DataFields/F, /Forms/F/Controls/C) narrows to that member. Label targets carry their en-US text. Empty results can mean the cross-reference data was never built for the referencing model: run reference_reindex on it and retry.

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": {
      "id": "<id>",
      "direction": "<direction>"
    },
    "name": "reference_references"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
kindNo
limitNo
offsetNo
directionYes

Output Schema

NameRequiredDescriptionDefault
okYes
errorNo
itemsNo
limitYes
totalYes
offsetYes
freshnessNo
truncatedYes
nextOffsetYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.16.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description does add real behavioral context: results are bounded, label targets carry en-US text, and empty results can be a data-not-built condition rather than a true zero. It says nothing about pagination behavior despite limit/offset existing.

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?

Front-loaded with the core action, then scope rules, then the troubleshooting fallback; every sentence carries information. The long parenthetical path enumerations are dense but genuinely useful for constructing ids correctly.

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?

An output schema exists, so return-value detail is not required, and the description wisely stays focused on id scope and empty-result handling. For a five-parameter, zero-coverage schema it is still incomplete, since kind, limit, and offset have no meaning anywhere.

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 description coverage is 0%, so the description carries the full burden. It explains id semantics thoroughly (artifact path vs member path, path syntax) and implies direction from 'incoming or outgoing', but never mentions kind, limit, or offset, leaving three of five parameters unexplained in both schema and prose.

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?

Names a specific verb and resource ('Read bounded incoming or outgoing typed reference edges') and precisely scopes what an artifact id versus a member id covers, including extensions and metadata links. It never names the closest siblings (reference_graph, reference_impact, ide_references), so an agent must infer differentiation from the 'bounded' qualifier alone.

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?

Gives a concrete routing rule: empty results mean the cross-reference data was never built, so run reference_reindex and retry. It also explains which id form to choose for artifact-level versus member-level queries. It stops short of saying when to prefer this over reference_graph or reference_impact.

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