Skip to main content
Glama

Ask the user to step in

writ_browser_ask_user

Hands an open session to the Writ user: kind='captcha' (they complete a security check in the live browser), 'twofa' (they supply the one-time code and Writ types it; the code never reaches this conversation), 'sign_in' (they sign in on the live page; no persona applies) or 'question' (their text answer). The call that opens the ask returns at once with user_link + tell_user to relay; later calls hold up to 60 s and answer answered, waiting_for_user (the same call again) or expired. Their answer is kept if your turn ends first.

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_ask_user"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNocaptcha | twofa | sign_in | question.
questionNokind='question': one short sentence.
session_idYes
wait_secondsNoHold up to this long (1-60).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"captcha | twofa | question."New value: +"captcha | twofa | sign_in | question."
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "captcha",
      -  "question",
      -  "twofa"
      -]New value: +[
      +  "captcha",
      +  "question",
      +  "twofa",
      +  "sign_in"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"captcha: the user completes a check in the live browser. question: the user answers in text. twofa: the user supplies the one-time code the page is asking for; Writ types it server-side and returns `entered`, never the code."New value: +"captcha | twofa | question."
    • changedInput schema / properties / question / description
      Previous value: -"The question, in one short sentence (required for kind 'question')."New value: +"kind='question': one short sentence."
    • changedInput schema / properties / wait_seconds / description
      Previous value: -"Hold up to this long (1-60, default 60)."New value: +"Hold up to this long (1-60)."
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (which only flag non-read-only, open-world, non-idempotent, non-destructive), it discloses the async protocol: the opening call returns immediately with user_link + tell_user, later calls block up to 60 s, and outcomes are answered / waiting_for_user / expired. It also adds a security-relevant guarantee that the one-time code never reaches the conversation and that answers survive if the agent's turn ends.

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?

Front-loaded with the core action, then a compact enumeration of kinds, then the call/lifecycle behavior. Dense but tightly packed, with each clause (return fields, 60 s hold, outcome states, answer persistence) contributing information; the parenthetical clauses are long but not redundant.

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?

With no output schema, the description wisely explains the return shape (user_link + tell_user) and all three polling outcomes, plus the security guarantee, which is what an agent needs to drive this asynchronous flow. Minor gaps remain on session_id provenance and what happens if the user never responds before an ask expires, but the critical protocol is complete.

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 coverage is 75%, so the schema already names the enum values and the 1-60 wait range. The description still adds real meaning the schema lacks: what the user actually does for each kind, that no persona applies to sign_in, and that question expects 'their text answer'. Only session_id is left unexplained.

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?

Names a specific action and resource ('hands an open session to the Writ user') and then enumerates the four distinct modes so the agent knows exactly what each invocation does. Sibling tools like writ_browser_act or writ_browser_live_view are clearly different in kind, and the description makes the handoff-to-human nature unambiguous.

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?

The four kinds effectively describe when to call this tool: security check, one-time code, live sign-in, or a text question. It does not explicitly exclude or point to a sibling alternative, but the mode taxonomy carries most of the selection guidance an agent needs.

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.