Skip to main content
Glama
Sign In
umbra

umbra

by lxchx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Aria Type

aria_type

Types text into an ARIA input field by index using human-like keystrokes by default to reduce bot-detection risk; set humanize=false for instant CDP input.

Instructions

Type into ARIA input by idx. humanize=True (default)=log-normal keystroke + pair-classification (~80-150ms/char, defeats cadence detectors). False=instant CDP keys (detectable). For multi-field use fill_form; for big paste use paste_text.

Ex: aria_type('t0', 1, 'me@example.com') → {"ok":true}

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": {
      "tab_id": "<tab_id>",
      "idx": "<idx>",
      "text": "<text>"
    },
    "name": "aria_type"
  }
}

Input Schema

NameRequiredDescriptionDefault
idxYes
textYes
clearNo
tab_idYes
humanizeNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden and does well: it discloses that humanize=True uses log-normal keystroke timing plus pair-classification at ~80-150ms/char to defeat cadence detectors, whereas False sends instant CDP keys that are detectable. It stops short of stating that `clear` defaults to wiping the field first or what happens on a failed/absent idx, leaving some side-effect behavior undisclosed.

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?

Dense and front-loaded: the core action leads, the humanize tradeoff follows, and alternatives come last, with a concrete call/response example. The telegraphic style ("Ex:", "~80-150ms/char") packs information efficiently but is slightly harder to parse than plain prose.

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?

An output schema exists, so return values need no explanation, and an inline example confirms the `{"ok":true}` shape anyway. Given the tool's simplicity and its solid coverage of the stealth/speed tradeoff — the only genuinely non-obvious behavior — what remains missing (clear semantics, tab_id meaning) is minor.

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

Parameters3/5

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

Schema description coverage is 0% across 5 params, and the description only adds meaning for `humanize` (richly) and implicitly for `idx`/`text` via the example. `tab_id` and `clear` — including that clear defaults to true and will erase existing content — are never explained, so roughly two of five parameters remain undocumented anywhere.

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 verb (type), target resource (ARIA input), and locator strategy (by idx), so the action is unambiguous. It also names the siblings it is not (fill_form for multi-field, paste_text for large pastes), letting an agent route correctly without opening other schemas.

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 routes alternatives: multi-field work goes to `fill_form`, big paste goes to `paste_text`, and this tool is the single-field keystroke path. It also gives the decision criterion for the humanize flag (stealth vs. speed/detectability), which is the main usage choice an agent faces.

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

Deploy Server

Other Tools