Skip to main content
Glama

screen_hand_over

Idempotent

Hand the open page to the USER for something only they should do (sign in, enter a code, accept a prompt) and wait. They see the page large in the Arsaze window, type into it there and press Done. You never see what they typed: those fields read as secret in screen_look and show as dots in screenshots and takes. Nothing is recorded meanwhile. Returns done: true when they finished (then screen_look), or done: false (cancelled or timed out: ask them before trying again). Web pages on the desktop app only; in one of their own apps they simply type it themselves.

response_detail (summary|ids|compact|full), fields (dotted paths), cursor (next page) — see the server instructions.

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": {
      "reason": "<reason>"
    },
    "name": "screen_hand_over"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNo
cursorNo
fieldsNo
reasonYes
secondsNo
response_detailNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly/destructive/idempotent flags say nothing about the human-in-the-loop mechanics): it explains that the user sees the page large in the Arsaze window, that typed values are never visible to the agent, are masked as secret in screen_look and as dots in screenshots and recordings, and that nothing is recorded during the handover. It also discloses both terminal states and how to react to each.

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

Conciseness4/5

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

The core is front-loaded and dense with useful detail in two sentences with no filler. The appended 'response_detail (summary|ids|compact|full), fields (dotted paths), cursor (next page) — see the server instructions' reads like a boilerplate footer and is the least integrated part, though it does carry information.

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?

Behavior and outcome handling are well covered for a blocking, human-in-the-loop tool with no output schema, and the done:true/done:false return values are stated. However, with 0% schema coverage on six params, the required 'reason', the timeout 'seconds', and 'ref' remain unexplained, leaving a real gap an agent must guess around.

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 0% across six parameters, so the description must carry the semantics, and it only partially does. It glosses response_detail, fields, and cursor in a trailing parenthetical, but never explains the required 'reason' argument, the 'seconds' timeout (only indirectly hinted at by 'timed out'), or what 'ref' selects.

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?

States a specific action (hand the open page to the USER) and its exact scope (actions only a human should perform: sign in, enter a code, accept a prompt) plus the blocking behavior (and wait). This is clearly separable from siblings like screen_act, screen_login, and screen_look without opening any schema.

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 explicit when-to-use (only-they-can-do-it steps), when-not-to-use (in one of their own apps they simply type it themselves; web pages on the desktop app only), and follow-up guidance after each outcome ('then screen_look' on done:true; 'ask them before trying again' on done:false).

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.