Skip to main content
Glama

Use an authorized browser session

vault_browser_action
Destructive

Queue one structured action in a user-controlled authenticated browser profile. Browser cookies/session storage remain on the worker. Returns a job_id; call vault_browser_result until complete.

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": {
      "profile_id": "<profile_id>",
      "action": "<action>"
    },
    "name": "vault_browser_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
risk_hintNo
profile_idYes
human_approvedNo
intent_lease_idNoOptional active task-scoped Intent Lease. When supplied, it further narrows this browser action and consumes one lease action.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, so the risk profile is known. The description adds genuine context beyond that: cookies and session storage stay on the worker, and the call is asynchronous, returning a job_id that must be polled. It does not explain what a destructive action can destroy, whether human_approved gates execution, or what risk_hint does, which are significant omissions for a destructive, non-idempotent tool.

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, front-loaded with the operation and its trust boundary, followed by the return/continuation contract. No filler and nothing redundant with the schema.

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?

For a destructive, open-world, non-idempotent tool wrapping a large nested action schema with no output schema, the description is thin. It omits approval semantics, what destructive actions can affect, and any per-action-type guidance, so an agent cannot confidently construct the action object from this text alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% with five top-level parameters and a nested action object containing roughly twenty mostly undocumented fields. The description explains only the return contract (job_id) and says nothing about profile_id, the action.type enum values, timeout_ms/wait_until semantics, human_approved, or risk_hint. Only intent_lease_id is documented, and that documentation lives in the schema rather than the description.

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 uses a specific verb and resource: 'Queue one structured action in a user-controlled authenticated browser profile,' which tells an agent this is an enqueue operation against a real browser session rather than a direct call. It also distinguishes itself from the sibling vault_browser_result by naming that tool as the completion step. It stops short of a 5 only because the kinds of actions (navigate/click/type/download) that make up the 'action' object are never mentioned.

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?

There is one clear procedural guideline: call vault_browser_result until complete after receiving a job_id. However, there is no guidance on when to prefer this over vault_execute or vault_invoke_write, no mention of when human_approved or intent_lease_id should be supplied, and no exclusions or preconditions beyond 'user-controlled authenticated profile'.

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.

Resources