Compose Preview Catalogs

ui_builder_get_guidelines

Read a design's latest design-guidelines result, whoever ran it — a person in the editor on their own key, ui_builder_check_design on this host's key, or an agent that recorded verdicts with ui_builder_record_guidelines. Returns the record (model, revision, rules asked, verdicts, ranBy), the findings it implies, and stale: true when the design has changed since it was checked.

Input Schema

TableJSON Schema

Name	Required	Description
`token`	No	A grant token from poll_access, when you cannot set the X-Compose-Preview-Token header yourself — an MCP client fixes its headers at connect time, so this is how a token approved during this session is used in it. Prefer the header where you control it.
`designId`	Yes
`agentName`	No	Optional agent/client name shown to design viewers; self-reported.
`agentModel`	No	Optional current model name shown to design viewers; self-reported. Omit when unknown.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`stale`	No
`record`	No
`schema`	Yes
`summary`	Yes
`designId`	Yes
`findings`	No
`unanswered`	No
`currentRevision`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

changedOutput schema / properties / findings / items / properties / measured / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "height": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "ratio": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "required": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "unit": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "width": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "height": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ratio": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "required": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "theme": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "unit": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "width": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed1 schema field changedOct 9, 2026

changedOutput schema / properties / record / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "asked": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "designId": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "model": {
-        "type": "string"
-      },
-      "ranBy": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "recordedAtEpochMillis": {
-        "anyOf": [
-          {
-            "type": "integer"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "revision": {
-        "type": "integer"
-      },
-      "rulesVersion": {
-        "type": "integer"
-      },
-      "schema": {
-        "type": "string"
-      },
-      "verdicts": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "confidence": {
-              "type": "number"
-            },
-            "nodeIds": {
-              "items": {
-                "type": "string"
-              },
-              "type": "array"
-            },
-            "reason": {
-              "type": "string"
-            },
-            "ruleId": {
-              "type": "string"
-            },
-            "verdict": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "ruleId",
-            "verdict"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      }
-    },
-    "required": [
-      "revision",
-      "model",
-      "rulesVersion",
-      "asked",
-      "verdicts"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "asked": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "costUsd": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "designId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "generationId": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "model": {
+        "type": "string"
+      },
+      "provider": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "ranBy": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "recordedAtEpochMillis": {
+        "anyOf": [
+          {
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "revision": {
+        "type": "integer"
+      },
+      "routing": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "probability": {
+                "anyOf": [
+                  {
+                    "type": "number"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "reason": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              },
+              "router": {
+                "type": "string"
+              },
+              "scores": {
+                "additionalProperties": {
+                  "type": "number"
+                },
+                "type": "object"
+              },
+              "version": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ]
+              }
+            },
+            "required": [
+              "router"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "rulesVersion": {
+        "type": "integer"
+      },
+      "schema": {
+        "type": "string"
+      },
+      "servedModel": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "verdicts": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "confidence": {
+              "type": "number"
+            },
+            "nodeIds": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            "reason": {
+              "type": "string"
+            },
+            "ruleId": {
+              "type": "string"
+            },
+            "verdict": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "ruleId",
+            "verdict"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      }
+    },
+    "required": [
+      "revision",
+      "model",
+      "rulesVersion",
+      "asked",
+      "verdicts"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

AddedOct 8, 2026

TDQS

A4.1/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it does meaningful work: it names the returned record fields (model, revision, rules asked, verdicts, ranBy), the implied findings, and the `stale: true` flag with its exact trigger (design changed since checked). It does not cover auth requirements, the token/header path, or any access constraints, leaving a gap for an unannotated tool.

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 and resource, then a second sentence enumerating the return contents and staleness. Two dense sentences with little waste, though the first sentence is long and packs producer routing, return shape, and source-of-truth into one clause.

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?

An output schema exists, so return values needn't be re-explained, yet the description usefully summarizes them and adds staleness semantics that the schema alone would not convey. For a read tool with no annotations the safety profile is low-risk, but auth/token handling is left entirely to the schema.

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 75%, and the token and agentName/agentModel parameters are documented in the schema. The description adds no parameter-level meaning (designId is bare in both), so this is the baseline 3 where the schema does the heavy lifting.

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?

States a specific verb (Read) and resource (latest design-guidelines result) and immediately disambiguates against siblings by naming the three producers — a person, ui_builder_check_design, or ui_builder_record_guidelines. An agent can tell this is the read-side companion to those write/run tools without opening a schema.

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 'latest... whoever ran it' framing tells the agent this fetches existing results rather than re-running a check, which implicitly routes it away from ui_builder_check_design. It stops short of an explicit 'use when X, not Y' statement or listing any exclusion, so it is clear context rather than full when/when-not guidance.

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

All Compose Preview Catalogs tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.