CompanyGraph

describe_relations

What the schemas declare between types: references with form and cardinality, ownership, enums, joins, list kinds. Use for a diagram or audit; for one type's full schema use describe_schema. Optional type narrows every list, direction (declares, declared-to, both; needs type) one side of relations, via relations and enums. Returns those lists, with forms and reading explaining every term. Not paged.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`via`	No
`type`	No
`direction`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`enums`	Yes
`forms`	Yes
`joins`	Yes
`lists`	Yes
`model`	Yes
`reading`	Yes
`ownership`	Yes
`relations`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedSep 21, 2026

addedInput schema / properties / direction

Added value: +{
+  "enum": [
+    "declares",
+    "declared-to",
+    "both"
+  ],
+  "type": "string"
+}

addedInput schema / properties / type
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / via
```
Added value: +{
+  "type": "string"
+}
```
changedOutput schema / additionalProperties
```
Previous value: -{}New value: +false
```

addedOutput schema / properties / enums

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "required": {
+        "type": "boolean"
+      },
+      "tokens": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "type": {
+        "type": "string"
+      },
+      "via": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "via",
+      "tokens",
+      "required",
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / forms

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

addedOutput schema / properties / joins

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "kind": {
+        "type": "string"
+      },
+      "section": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "section",
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / lists

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "kind": {
+        "type": "string"
+      },
+      "min": {
+        "maximum": 9007199254740991,
+        "minimum": 0,
+        "type": "integer"
+      },
+      "required": {
+        "type": "boolean"
+      },
+      "section": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "section",
+      "kind",
+      "required",
+      "min",
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / ownership

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "owned": {
+        "type": "string"
+      },
+      "owner": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "owner",
+      "owned"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / reading

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

addedOutput schema / properties / relations

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "array": {
+        "type": "boolean"
+      },
+      "form": {
+        "enum": [
+          "ref",
+          "ref?",
+          "qualifier"
+        ],
+        "type": "string"
+      },
+      "from": {
+        "type": "string"
+      },
+      "max": {
+        "anyOf": [
+          {
+            "maximum": 9007199254740991,
+            "minimum": 0,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "min": {
+        "maximum": 9007199254740991,
+        "minimum": 0,
+        "type": "integer"
+      },
+      "required": {
+        "type": "boolean"
+      },
+      "to": {
+        "type": "string"
+      },
+      "via": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "from",
+      "via",
+      "to",
+      "form",
+      "array",
+      "required",
+      "min",
+      "max"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "model"
-]New value: +[
+  "relations",
+  "ownership",
+  "enums",
+  "joins",
+  "lists",
+  "forms",
+  "reading",
+  "model"
+]

First observedSep 21, 2026

TDQS

A4.8/5.0

Behavior4/5

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

With no annotations, the description takes on the full burden. It discloses return shape ('Returns those lists'), explains output terms ('with `forms` and `reading` explaining every term'), and states pagination behavior ('Not paged'). It also reveals a parameter dependency ('needs `type`'). It does not explicitly state read-only/safety, but the verb 'describe' and introspection-focused phrasing make that highly implicit.

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?

Three sentences cover purpose, usage, parameters, return format, and pagination without waste. The purpose is front-loaded and the alternative tool is named immediately. Each clause earns its place, and the dense style remains readable.

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 tool with three optional interdependent parameters and no required inputs, the description covers all essential bases: what it returns, how to filter, when to use it instead of a sibling, and the output schema is provided separately. The 'Not paged' note removes a common ambiguity. Nothing needed for correct invocation is missing.

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?

Schema description coverage is 0%, so the description must compensate, and it does. Every parameter is explained: `type` narrows every list, `direction`'s enum values are listed with its dependency on `type`, and `via` filters relations and enums. This adds meaning far beyond the raw schema.

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 defines the tool's output as 'what the schemas declare between types' with specific artifacts (references, ownership, enums, joins, list kinds), making the resource and scope unmistakable. It also explicitly contrasts with describe_schema, telling the agent exactly when this tool is not the right one. This qualifies as a specific verb+resource with sibling differentiation.

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 explicitly says 'Use for a diagram or audit' and points to describe_schema as the alternative for one type's full schema. This gives clear context for when to invoke this tool and when to turn elsewhere. The optional parameter explanations further guide usage for narrowing results.

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

All CompanyGraph 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?