WebRun Browser Automation

Send task to session

send_task

Destructive

Send a new task to an existing browser session (from create_session). The real Chrome browser may navigate, fill forms, and submit data on third-party websites as the task requires.

Input Schema

TableJSON Schema

Name	Required	Description
`files`	No	Optional file IDs to attach (from /files/upload). Max 5 files.
`prompt`	Yes	Task description
`secrets`	No	Domain-matched secrets [{match, fields}] (not stored)
`webhook`	No	Webhook configuration
`sessionId`	Yes	Session ID from create_session
`outputType`	No	Response format
`maxDuration`	No	Max duration for this task in minutes (3-60). Defaults to the value the session was created with.
`startingUrl`	No	URL to navigate to before starting this task (optional)
`outputSchema`	No	JSON Schema for structured output (required if outputType is structured_json)
`maxInputTokens`	No	Max input tokens for this task (100-3000000). Defaults to the value the session was created with.
`maxOutputTokens`	No	Max output tokens for this task (100-1000000). Defaults to the value the session was created with.
`terminateOnCompletion`	No	Auto-terminate after task (default: false)

Output Schema

TableJSON Schema

Name	Required	Description
`data`	No	Task output payload (instance-authored shape)
`type`	No	Result type, e.g. 'task_completed', 'task_failed', 'guardrail_trigger'
`error`	No
`status`	No	Present on guardrail results: 'awaiting_input'
`taskId`	No
`message`	No
`pending`	No	True when the task is still running — poll get_task_status
`success`	No
`sessionId`	No
`environment`	No
`liveViewURL`	No	Page for watching the run live, present while it is still running or awaiting input. The only URL here that is safe to show a user or open in a browser.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedAug 26, 2026

addedOutput schema / properties / liveViewURL

Added value: +{
+  "description": "Page for watching the run live, present while it is still running or awaiting input. The only URL here that is safe to show a user or open in a browser.",
+  "type": "string"
+}

Changed4 schema fields changedAug 23, 2026

addedInput schema / properties / maxDuration

Added value: +{
+  "description": "Max duration for this task in minutes (3-60). Defaults to the value the session was created with.",
+  "type": "number"
+}

addedInput schema / properties / maxInputTokens

Added value: +{
+  "description": "Max input tokens for this task (100-3000000). Defaults to the value the session was created with.",
+  "type": "number"
+}

addedInput schema / properties / maxOutputTokens

Added value: +{
+  "description": "Max output tokens for this task (100-1000000). Defaults to the value the session was created with.",
+  "type": "number"
+}

addedInput schema / properties / startingUrl

Added value: +{
+  "description": "URL to navigate to before starting this task (optional)",
+  "type": "string"
+}

Changed1 schema field changedAug 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Task outcome envelope: a completion (success/type/data), a pending marker (poll get_task_status), or an awaiting_input guardrail. `data` is the task output; its shape is task-defined (freeform text or the caller-supplied structured schema).",
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "description": "Task output payload (instance-authored shape)",
+      "type": "object"
+    },
+    "environment": {
+      "properties": {
+        "environmentId": {
+          "type": "string"
+        },
+        "name": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      },
+      "type": "object"
+    },
+    "error": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "pending": {
+      "description": "True when the task is still running — poll get_task_status",
+      "type": "boolean"
+    },
+    "sessionId": {
+      "type": "string"
+    },
+    "status": {
+      "description": "Present on guardrail results: 'awaiting_input'",
+      "type": "string"
+    },
+    "success": {
+      "type": "boolean"
+    },
+    "taskId": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "type": {
+      "description": "Result type, e.g. 'task_completed', 'task_failed', 'guardrail_trigger'",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedAug 8, 2026

TDQS

A4/5.0

Behavior4/5

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

The annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, so the agent knows this is a side-effectful, open-world operation. The description adds valuable context: 'The real Chrome browser may navigate, fill forms, and submit data on third-party websites as the task requires.' This goes beyond the annotations by specifying actual behaviors, which helps the agent anticipate side effects. No contradiction.

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?

The description is two sentences, front-loaded with the core purpose, followed by a contextual note about browser behavior. Every word earns its place; there is no redundancy or filler.

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 that the schema covers all parameters and an output schema exists to define return values, the description provides the essential context: the purpose and the real-browser behavior that may have side effects. It could mention prerequisites like needing a valid session ID from create_session, but that is implied and captured in the schema. The description is sufficiently complete for an agent to understand what the tool does and what to expect, though it could briefly mention state changes or error conditions.

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?

The input schema provides 100% coverage for all 12 parameters, each with descriptive text. The description itself does not add any additional meaning to the parameters beyond what the schema already states. Since the schema covers everything, the baseline of 3 is appropriate.

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 sends a new task to an existing browser session, tying it to create_session. It specifies the verb 'send' and the resource 'task'. However, it does not explicitly differentiate from potentially similar tools like browser_task or create_workflow, relying on the context of 'existing session' to distinguish. This is clear but could be more explicit about its unique role among siblings.

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 description gives clear context: use for existing sessions created via create_session. This implies a workflow where create_session precedes this tool. However, it does not provide any exclusions or mention when to use alternative tools, such as browser_task for direct browsing or create_workflow for multi-step tasks. The context is clear but not comprehensive.

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

All WebRun Browser Automation tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation5/5

Each tool targets a distinct resource and action: ad-hoc tasks (browser_task), persistent sessions (create_session/send_task), workflows (create/get/update/trigger), agents (create/list/pause/resume), and session control (pause/resume/stop/terminate). The descriptions explicitly disambiguate overlapping-looking tools like browser_task vs trigger_workflow, making accidental misselection unlikely.

Naming Consistency4/5

The vast majority follow a clear verb_noun pattern (create_workflow, list_agents, pause_session_task, trigger_workflow, etc.). Minor deviations exist: browser_task and guardrail_response are noun_noun, and screenshot is a single word, but these are understandable and do not disrupt the overall pattern.

Tool Count3/5

With 21 tools the set is on the heavy side, fitting the 16-25 borderline range. Each tool has a distinct purpose, but the count feels slightly inflated due to granular session/task control (pause, resume, stop, terminate) and separate workflow/agent management that could potentially be consolidated.

Completeness3/5

Workflows have create/read/update/list/trigger coverage, and sessions/tasks have robust lifecycle control, but there are notable gaps: no delete_workflow or delete_agent, and agents lack update functionality. While core automation flows are supported, lifecycle management is incomplete without deletion or editing of scheduled agents.

Resources

Need Help?