Skip to main content
Glama

Apple entity cross-references

apple_cross_references
Read-onlyIdempotent

Retrieve incoming and outgoing cross-reference edges for a session, API, proposal, or sample to find related sessions, covered APIs, and implementation links.

Instructions

Returns outgoing and/or incoming edges from the cross-reference graph for a given entity. Use to find: which sessions mention an API, which proposals a session implements, which APIs a session covers, related sessions. Build the graph with npm run ingest -- --source cross-reference.

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": {
      "entity_type": "<entity_type>",
      "entity_id": "<entity_id>"
    },
    "name": "apple_cross_references"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoResponse formatmarkdown
directionNo'out' = edges FROM this entity, 'in' = edges TO this entity, 'both' = all.both
entity_idYesEntity ID, e.g. 'wwdc2024-10016' for a session, 'swiftui/view' for a doc, 'SE-0428' for a proposal.
entity_typeYesType of the entity.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.3
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv0.2.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no restating. The description does add one genuinely useful operational fact beyond them — that results depend on an ingest step ('npm run ingest -- --source cross-reference'), implying empty output before that build. It stops short of describing return shape or behavior when the entity or graph is missing.

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?

Three short, well-ordered sentences: purpose first, then use cases, then the build prerequisite. The npm command is arguably infrastructure detail, but it is placed last where it does not obstruct the core statement.

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?

There is no output schema, so the description carries the burden of explaining what an edge looks like — node types, labels, directionality in the payload — and it does not. For a graph traversal tool whose whole value is the returned edge structure, that is a real gap, though the four use-case examples partly compensate by implying what comes back.

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 coverage is 100% and three of four parameters have enums with inline semantics, including the out/in/both direction definition. The description's phrase 'outgoing and/or incoming' merely echoes that, adding no format examples or ID conventions beyond what the schema already documents.

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?

States a specific verb and resource: 'Returns outgoing and/or incoming edges from the cross-reference graph for a given entity.' The follow-up examples ('which sessions mention an API', 'which APIs a session covers') make the resource concrete. It doesn't explicitly distinguish itself from near-siblings like wwdc_related_sessions or apple_what_replaced, which keeps it off a 5.

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?

The 'Use to find:' list gives four concrete query shapes, which is clear positive guidance on when to reach for this tool. What's missing is exclusions — nothing says when to prefer wwdc_related_sessions or a direct get tool over this graph traversal.

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