Skip to main content
Glama

Live browser view

writ_browser_live_view
Idempotent

The live browser card's own access: the card ChatGPT and Claude show under writ_browser_use and writ_record_website calls it to read the session's state and get one-time passes for the session's screencast and its take-over channel. The user watches the page in the card and can take it over there. It is not part of a conversation's work.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_id": "<session_id>"
    },
    "name": "writ_browser_live_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
session_idYesThe session_id the card was opened with (cbs_...).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.8/5.0
Behavior3/5

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

The annotations say readOnlyHint=false and idempotentHint=true without explaining why; the description usefully accounts for the non-read-only flag by explaining it issues one-time passes for screencast and take-over channels, and it discloses that a human may be watching and take control of the page concurrently. That is real behavioral context beyond the annotations, but it leaves open what 'state' is returned and how long a pass remains valid, and 'one-time passes' sits in mild tension with idempotentHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no obvious padding, but the opening clause ('The live browser card's own access:') is syntactically awkward and front-loads an abstraction instead of the verb. The ordering buries the two concrete operations behind explanation of the card's surface.

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

Completeness3/5

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

Parameter documentation is fully handled by the schema and safety hints by the annotations, but with no output schema the description should say what 'the session's state' and a 'pass' actually look like, and it should state plainly whether an agent is ever expected to call this. As written, an agent has enough to avoid misusing the tool but not enough to use it competently.

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?

Only one parameter exists and the schema already documents it fully, including the cbs_ prefix format. The description adds nothing to session_id beyond implying it identifies the session whose state is read, so the baseline of 3 for high schema coverage applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names specific operations — reading the session's state and obtaining one-time passes for the screencast and take-over channel — which is more than a restatement of the name. However, the framing as 'the live browser card's own access' is opaque and reads as meta-commentary about a UI surface rather than a task an agent would perform, so the actual purpose takes effort to extract.

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

Usage Guidelines2/5

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

There is a negative signal ('It is not part of a conversation's work'), which hints the agent generally should not call this, but it is ambiguous and no positive when-to-use condition or named alternative (e.g. a sessions/context sibling) is offered. The mentions of writ_browser_use and writ_record_website describe where the card appears, not when to select this tool over them.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.