Skip to main content
Glama

page_geetest_slide

Solves GeeTest v3 slide puzzles from live pages and performs the human drag by extracting the three canvases, computing the exact hole offset, and moving the slider. Returns JSON with drag_x, hole bounds, and piece_x0.

Instructions

GEETEST SLIDE SOLVER: solve the GeeTest v3-style slide puzzle from the live page, then perform the human drag itself. Extracts the three canvases (bg, puzzle slice, full reference bg) via toDataURL, finds the hole with |bg-fullbg| diff + largest-blob + morphological closing (the JPEG-noise trap), measures the piece's solid-alpha left edge, and drags the slider by hole_x0 - piece_x0 with the engine's humanized mouse. Returns JSON {drag_x, hole: [x0, x1], piece_x0}. Call AFTER the challenge popup is open. No vision model, pure pixel math.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
page_idYes
session_idYes
slider_refNoOptional ref of the slider handle (.geetest_slider_button). If omitted the tool locates it by selector and registers its own ref.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.3

TDQS

A4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden, and it does so well: it discloses the canvas extraction, diff-based hole detection algorithm, slider drag calculation, and that it performs a humanized mouse drag. It does not mention side effects or failure conditions, but the core behavioral surface is clearly communicated.

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 a dense, front-loaded paragraph with a clear action statement followed by implementation details, return shape, and call timing. It is longer than the minimal case but every sentence adds meaningful information for a complex automated solver; it earns its length without becoming bloated.

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?

Given the complexity of the tool and the absence of an output schema, the description does a good job explaining the return JSON shape and the high-level algorithm. It is missing explicit semantics for the required parameters and does not mention edge cases, but for an agent selecting and invoking this captcha solver, the essential context is present.

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 only 33%, and the description does not compensate for the undocumented required session_id and page_id parameters. It gives useful context about the live page and slider, but it never explains how the parameters map to the tool's operation, leaving the agent to guess the role of the required inputs.

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 states a specific verb and resource: it 'solve[s] the GeeTest v3-style slide puzzle from the live page, then perform[s] the human drag itself.' It clearly differentiates from sibling tools like page_geetest_click by focusing on the slide drag behavior and explicitly calling out that it uses 'pure pixel math' rather than a vision model.

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 description provides clear timing guidance with 'Call AFTER the challenge popup is open,' and implies this tool handles the slide drag, not other captcha types. It does not explicitly name alternatives or say when not to use it, but the context is strong enough for an agent to know when this tool is appropriate.

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