Skip to main content
Glama
mienetic

Ghostvault

by mienetic

Detect Login Options on Page

gv_detect_login_options
Read-only

Scans a webpage to detect available login options such as SSO buttons, form fields, 2FA, and captcha, then recommends the optimal login path automatically.

Instructions

Scan the current page (or a URL) for available login options.

Detects SSO buttons (Google, GitHub, Facebook, etc.), username/password form fields, 2FA/OTP fields, and captcha. Returns a recommendation on which login path to take.

Use this BEFORE gv_sign_in when you're not sure what the page offers — it helps the agent decide whether to auto-fill, click an SSO button, or let the user log in manually.

DECISION GUIDE — what to do with the result:

  • recommendation="sso:google" → click the SSO button for that provider

  • recommendation="form" → use gv_sign_in with stored credentials

  • recommendation="ask_user" → multiple SSO options found; ASK the user which provider they want to use

  • recommendation="manual" → no form/SSO detected; let user do it manually (the browser window is already open)

In ALL cases, the session is saved automatically — the user only needs to log in once per account.

Args: url: Optional URL to navigate to before scanning. If omitted, scans the current page.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1-beta

TDQS

A4.9/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true, and the description adds that the tool only scans and returns a recommendation, with no side effects. It also notes that the session is saved automatically, providing useful behavioral context beyond annotations.

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 description is well-structured with clear sections and front-loaded key info. It is somewhat lengthy but every sentence adds value; no redundancy. Could be slightly trimmed without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with an output schema (implied), the description covers all necessary aspects: purpose, usage decision guide, parameter semantics, and behavioral notes. It is fully self-contained and actionable.

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

Parameters5/5

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

Despite 0% schema description coverage, the description fully explains the single parameter 'url': it is optional, navigates to that URL first, or scans the current page if omitted. This adds clear meaning beyond the schema.

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 clearly states it scans the page for login options and returns a recommendation. It uses specific verbs ('Scan', 'Detects', 'Returns') and distinguishes from sibling gv_sign_in by stating usage before that tool.

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?

Explicitly says 'Use this BEFORE gv_sign_in when you're not sure what the page offers' and provides a complete decision guide mapping recommendations to actions, including alternatives like asking the user.

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