Skip to main content
Glama

Resume a saved browser session

resume_saved_session

Resume an existing saved session owned by the connected account. Reuses an active browser with the label, otherwise opens one metered browser with a 180-second idle timeout, restoring cookies and storage, not tabs. Only call after the user requests resume. Never retry an ambiguous allocation or change requestId to retry. Close the returned browser when finished.

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": {
      "label": "<label>",
      "requestId": "<requestId>"
    },
    "name": "resume_saved_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelYes
requestIdYesUnique operation ID. Repeated calls for the same operation must use the same ID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare it is not read-only or destructive; the description goes far beyond by disclosing the reuse-vs-allocate behavior, metered browser usage, a 180-second idle timeout, and the exact restore boundary (cookies and storage, not tabs). The idempotency warning about ambiguous allocations and requestId reuse is exactly the kind of operational risk an agent needs.

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?

Five short sentences, each carrying a distinct fact: identity/ownership, allocation behavior, restore scope, invocation gating, retry prohibition, cleanup. The identifying scope and allocation behavior are front-loaded with zero 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?

For a mutating, resource-allocating tool with no output schema, the description covers allocation cost, timeout, restore scope, idempotency, and teardown. The remaining gap is the return value: 'the returned browser' implies a browser object but no identifier or field is named, so an agent must infer what to pass to close_browser.

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?

With only 50% schema description coverage, the description partially compensates: it ties 'label' to the saved session being resumed and reinforces requestId idempotency ('same operation must use same ID'). However, it never says where a valid label comes from or whether label/requestId need to match a prior session, leaving the undocumented 'label' parameter under-explained.

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?

States a specific verb and resource ('Resume an existing saved session') plus scope ('owned by the connected account') and what is restored ('cookies and storage, not tabs'). The verb is clearly distinct from get_saved_sessions and remove_saved_session, though no sibling is named explicitly.

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

Usage Guidelines5/5

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

Gives an explicit precondition ('Only call after the user requests resume'), a negative instruction ('Never retry an ambiguous allocation or change requestId to retry'), and a postcondition ('Close the returned browser when finished'). When-to-use, when-not-to-retry, and cleanup are all spelled out.

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