touch-browser

Overview Schema Source Related Servers Discussions Admin

Open Target

tb_open

Open public web documents headlessly for evidence extraction, using sessions or direct URLs with domain restrictions and risk labeling.

Instructions

Open a public web document or official reference page headlessly, either statelessly or inside a daemon session/tab. target is required for stateless use; with sessionId it can be omitted to reopen the active tab URL.

Input Schema

TableJSON Schema

Name	Required	Description
`target`	No	The URL or public web target to open. Required unless sessionId points at an opened active tab.
`browser`	No	When true, open the target through the browser-backed acquisition path.
`budget`	No	Token budget for snapshot and semantic processing. Default is 512.
`sourceRisk`	No	The source risk label to attach to the result or citation.
`sourceLabel`	No	The human-readable source label to attach to the result or citation.
`verifierCommand`	No	An optional verifier command to run for this operation.
`allowDomains`	No	Restrict navigation for this open request to these domains.
`sessionId`	No	An existing session to reuse for this open request.
`tabId`	No	A specific session tab to reuse for this open request.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`version`	No
`action`	No
`status`	No
`payloadType`	No
`output`	No
`diagnostics`	No
`policy`	No
`failureKind`	No
`message`	No
`sessionId`	No
`tabId`	No
`result`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv0.7.0Jun 12, 2026

addedInput schema / properties / allowDomains / description

Added value: +"Restrict navigation for this open request to these domains."

addedInput schema / properties / browser / description

Added value: +"When true, open the target through the browser-backed acquisition path."

addedInput schema / properties / budget / description

Added value: +"Token budget for snapshot and semantic processing. Default is 512."

addedInput schema / properties / sessionId / description

Added value: +"An existing session to reuse for this open request."

addedInput schema / properties / sourceLabel / description

Added value: +"The human-readable source label to attach to the result or citation."

addedInput schema / properties / sourceRisk / description

Added value: +"The source risk label to attach to the result or citation."

addedInput schema / properties / tabId / description

Added value: +"A specific session tab to reuse for this open request."

addedInput schema / properties / target / description

Added value: +"The URL or public web target to open. Required unless sessionId points at an opened active tab."

addedInput schema / properties / verifierCommand / description

Added value: +"An optional verifier command to run for this operation."

changedInput schema / required

Previous value: -[
-  "target"
-]New value: +[]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "minProperties": 1,
+  "properties": {
+    "action": {
+      "type": "string"
+    },
+    "diagnostics": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "failureKind": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "output": {
+      "additionalProperties": true,
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "payloadType": {
+      "type": "string"
+    },
+    "policy": {
+      "additionalProperties": false,
+      "properties": {
+        "allowlistedDomains": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "blockedRefs": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "decision": {
+          "type": "string"
+        },
+        "riskClass": {
+          "type": "string"
+        },
+        "signals": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "detail": {
+                "type": "string"
+              },
+              "kind": {
+                "type": "string"
+              },
+              "origin": {
+                "type": "string"
+              },
+              "stableRef": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "kind",
+              "origin",
+              "detail"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "sourceRisk": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "decision",
+        "sourceRisk",
+        "riskClass",
+        "blockedRefs",
+        "signals"
+      ],
+      "type": "object"
+    },
+    "result": {
+      "additionalProperties": false,
+      "properties": {
+        "action": {
+          "type": "string"
+        },
+        "diagnostics": {
+          "additionalProperties": true,
+          "type": [
+            "object",
+            "null"
+          ]
+        },
+        "failureKind": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        },
+        "output": {
+          "additionalProperties": true,
+          "type": [
+            "object",
+            "null"
+          ]
+        },
+        "payloadType": {
+          "type": "string"
+        },
+        "policy": {
+          "additionalProperties": false,
+          "properties": {
+            "allowlistedDomains": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            "blockedRefs": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            "decision": {
+              "type": "string"
+            },
+            "riskClass": {
+              "type": "string"
+            },
+            "signals": {
+              "items": {
+                "additionalProperties": false,
+                "properties": {
+                  "detail": {
+                    "type": "string"
+                  },
+                  "kind": {
+                    "type": "string"
+                  },
+                  "origin": {
+                    "type": "string"
+                  },
+                  "stableRef": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "kind",
+                  "origin",
+                  "detail"
+                ],
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "sourceRisk": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "decision",
+            "sourceRisk",
+            "riskClass",
+            "blockedRefs",
+            "signals"
+          ],
+          "type": "object"
+        },
+        "status": {
+          "type": "string"
+        },
+        "version": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "version",
+        "action",
+        "status",
+        "payloadType",
+        "message"
+      ],
+      "type": "object"
+    },
+    "sessionId": {
+      "type": "string"
+    },
+    "status": {
+      "type": "string"
+    },
+    "tabId": {
+      "type": "string"
+    },
+    "version": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedv0.1.11Apr 15, 2026

TDQS

B3.2/5.0

Behavior2/5

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

Discloses headless operation and session reuse, but with no annotations, the description does not cover side effects, error scenarios, resource impact, or whether the operation is read-only, leaving important behavioral gaps.

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?

Two sentences efficiently convey the core purpose and a key usage condition with no wasted words. Front-loaded and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 9 parameters and no annotations, the description is too sparse. It only addresses the target parameter's condition, leaving the purpose and implications of other parameters unexplained, and lacks overall usage guidance.

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%, so each parameter is already described. The description adds value by clarifying the target required condition for stateless vs session use, but does not enhance understanding of other parameters.

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?

The description clearly states the tool opens a public web document or official reference page headlessly, with specific verb and resource. It distinguishes from search and click tools but does not explicitly differentiate from the sibling tb_tab_open.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context on stateless versus session-based usage and when target is required, but lacks explicit guidance on when to choose this tool over alternatives or when not to use it.

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