Compose Preview Catalogs

ui_builder_record_guidelines

Record your own model's verdicts on ui_builder_guidelines_prompt as the design's latest design-guidelines result, so the editor's Issues panel and other agents show them. Pass the revision and rule ids the prompt asked (rules.asked[].id), and one verdict per rule you answered: pass, fail or not_applicable, with confidence 0..1, the nodeIds it is about and a one-sentence reason. ranBy is taken from your credential. Returns what ui_builder_get_guidelines returns.

Input Schema

TableJSON Schema

Name	Required	Description
`asked`	Yes	The rule ids the prompt asked.
`model`	Yes	The model that judged it, e.g. anthropic/claude-haiku-5.5.
`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
`revision`	Yes	The revision the prompt was built from.
`verdicts`	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.
`rulesVersion`	No	The prompt's `rules.version`. Defaults to this host's.

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 burden, and it does add real context: verdicts become the design's latest result visible to the editor and other agents, `ranBy` is derived from the credential rather than supplied, and the return mirrors ui_builder_get_guidelines. It does not describe failure modes, idempotency, or how the token/header auth interacts, which keeps it short of a 5.

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 purpose, then the required inputs, then the return. It is dense but each clause maps to a real field or behavior; the only minor cost is that the middle sentence is packed with several field explanations at once.

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?

Given 9 parameters, a nested verdicts object, and an output schema that already governs return values, the description covers the workflow and the credential-derived `ranBy` well. It omits explicit permission requirements, but nothing an agent needs to invoke it correctly is glaringly missing.

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 78%, so the schema already documents most parameters. The description reinforces the verdict shape (pass/fail/not_applicable, confidence 0..1, nodeIds, one-sentence reason) and ties `asked` to the prompt's `rules.asked[].id`, but much of this repeats the nested schema rather than adding new meaning.

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 and resource: recording the model's verdicts as the design's latest design-guidelines result. It clearly separates itself from the requesting sibling (ui_builder_guidelines_prompt) and the reading sibling (ui_builder_get_guidelines) by naming both the input prompt and the equivalent return.

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?

It explains the context of use – verdicts on the prompt asked by ui_builder_guidelines_prompt, recorded so the Issues panel and other agents see them. The workflow (answer the prompt, then record one verdict per rule) is clear, though there is no explicit 'do not use this when...' exclusion.

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.