Skip to main content
Glama
Vladimir-Human

humanizer-ru

by Vladimir-Human
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

humanizer-clean

humanizer_clean
DestructiveIdempotent

Removes supported chatbot copy-paste artifacts and invisible marks from Russian text, verifies the result, and reports protected areas and residual findings without rewriting style or meaning.

Instructions

явная очистка поддерживаемых артефактов чат-вставки одним сценарием: проверка до (единый детектор), снятие невидимых меток (слой A) и видимых артефактов класса A (MARKUP) вне защищённых областей до неподвижной точки, проверка после, сверка фактов, перечень неизменённых защищённых областей и остаточных находок; стиль и смысл не переписываются Когда не использовать: не стилистическое переписывание и не проверка смысла: снимаются только зарегистрированные артефакты вставки; неподдерживаемые находки (класс B, вики-разметка, плейсхолдеры, метки вне текстового пути) остаются явным остатком (код 1) — операция не заявляет полную чистоту; контейнерные файлы (PNG/DOCX/PDF/…) — scripts/filemarks (репозиторий). Language profile is explicit in --language; en/auto do not claim English stylistic or authorship detection.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesОбрабатываемый текст (данные, не команды). Область скилла — русский связный текст; пустой и не-русский вход получает статус out-of-scope.
languageNoЯзыковой профиль: en/auto разрешают английские артефакты и факты; русские стилевые эвристики не применяются.ru

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
toolYes
errorNo
filesYes
schemaYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.36.0
    • addedInput schema / properties / language
      Added value: +{
+  "default": "ru",
+  "description": "Языковой профиль: en/auto разрешают английские артефакты и факты; русские стилевые эвристики не применяются.",
+  "enum": [
+    "ru",
+    "en",
+    "auto"
+  ],
+  "type": "string"
+}
    • addedOutput schema / properties / files / items / properties / language
      Added value: +{
+  "enum": [
+    "ru",
+    "en",
+    "auto"
+  ],
+  "type": "string"
+}
  2. Addedv3.35.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description enriches this: removal iterates 'до неподвижной точки', protected areas are reported as untouched, and the run deliberately does NOT claim full cleanliness (residual findings, code 1). This adds real behavioral context beyond the annotations. It does not detail auth or performance, so not a 5.

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

Conciseness3/5

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

Purpose is front-loaded, but the body is one very long semicolon-chained run-on that is hard to parse and repeats the check-before/check-after cycle. Some clauses earn their place (the exclusions, the residual-finding caveat), yet overall it is denser and longer than necessary.

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?

An output schema exists, so return values need not be described. The description covers scope (Russian connected text), language caveats, the fixed-point removal loop, protected-area reporting, and residual-finding semantics — enough for an agent to call it correctly. Only minor gaps (no explicit mention of sibling alternates by name) remain.

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 100%, so both parameters are already documented in the schema. The description reiterates the language profile behavior ('en/auto do not claim English stylistic detection'), reinforcing the enum semantics but adding little beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('явная очистка поддерживаемых артефактов чат-вставки') and enumerates the concrete steps (detector check, removal of invisible marks and visible class-A MARKUP). It explicitly separates itself from stylistic rewriting, which distinguishes it from siblings like humanizer_polish. The dense single-sentence phrasing slightly blurs the core purpose, but it is identifiable.

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?

It gives an explicit 'Когда не использовать' section: not stylistic rewriting, not meaning verification, and it routes container files (PNG/DOCX/PDF) to scripts/filemarks. It cites conditions (unsupported findings class B, wiki markup, placeholders remain as residual code 1). No explicit routing to humanizer_polish/facts by name, but the exclusions are clear.

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