Skip to main content
Glama
camoufox-reverse-mcp

camoufox-reverse-mcp

stage_break

Arm a break on a specific dispatcher state to record bounded deep snapshots of arguments, return values, or filtered call stacks for focused JavaScript instrumentation debugging.

Instructions

Per-state deep capture for instrumentation(tap_stage_calls=True).

A stage tap only previews the first arguments. When one state has to be inspected properly, arm a break for that state id: every hit then records a bounded deep snapshot of the arguments (and optionally the return value and a filtered call stack) as a tap_stage_break event.

Armed states stay armed for this MCP session until "clear": the live page is updated at once, and every instrumented script served afterwards carries the armed set, so states that run while a page loads are captured after a reload. The limit counts hits per page load. Snapshots read own data properties only and report getters as {"__t": "accessor"} without calling them; a Proxy argument still sees its ownKeys/getOwnPropertyDescriptor traps.

Args: action: "set" arm one state, "clear" disarm (all when p is omitted), "list" show armed states and their hit counters. p: Dispatcher state id (the integer from tap_stage events). capture: "args_only" | "args_ret" (default) | "args_ret_stack". limit: Maximum recorded hits, 0 means unlimited (default 0). depth: Snapshot depth for nested objects/arrays (1-5, default 2). max_items: Maximum keys/elements kept per object/array (1-500, default 50).

Returns: dict with the states armed for later loads (session_armed), the live page's armed set and hit counters, and whether the instrumentation runtime is present on the page.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "stage_break"
  }
}

Input Schema

NameRequiredDescriptionDefault
pNo
depthNo
limitNo
actionNolist
captureNoargs_ret
frame_urlNo
max_itemsNo
frame_nameNo
frame_indexNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.10.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: armed states persist for the MCP session, the live page updates immediately, later-served scripts inherit the armed set so load-time states are captured after reload, and `limit` counts hits per page load. It also discloses snapshot semantics — own data properties only, getters reported as {"__t": "accessor"} uncalled, Proxy traps still firing — which is exactly the kind of side-effect detail 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?

Despite its length, every sentence earns its place: purpose, lifecycle/reload behavior, snapshot fidelity caveats, then a clean Args/Returns block. The critical constraint (armed-per-session) is front-loaded ahead of the parameter list.

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 complex, annotation-free stateful tool it covers the return payload (session_armed, live armed set, hit counters, runtime presence) and the persistence model thoroughly. The only shortfall is the unexplained frame_* parameters, which matter for a multi-frame browser tool.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate, and it documents six parameters with meaning and defaults (action modes, capture variants, limit=0 unlimited, depth 1-5, max_items 1-500). It leaves frame_url, frame_name and frame_index completely unexplained, which is a real gap across 9 parameters.

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

Purpose5/5

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

The description opens with a precise scope ("Per-state deep capture for `instrumentation(tap_stage_calls=True)`") and then contrasts it with the cheaper alternative: "A stage tap only previews the first arguments... arm a break for that state id." An agent can see this is a per-state deep-snapshot tool distinct from general instrumentation without opening the schema.

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?

It gives a clear triggering condition ("When one state has to be inspected properly") and explains the lifecycle via the action values set/clear/list, including that "clear" disarms all when `p` is omitted. It stops short of explicit when-not-to-use guidance or naming a sibling tool as the cheap alternative, which keeps it at 4.

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