Skip to main content
Glama

Humanize AI text

humanize_text

Rewrite AI-generated text so it reads like natural human writing and scores as human on AI detectors (GPTZero, Originality.ai, Copyleaks, Turnitin). Returns only the rewritten text: show it to the user verbatim, without commenting on its quality or editing it (its less polished phrasing is intentional). Spends words from the account balance (1 input word = 1 word; 3 words per input word with ultra).

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": {
      "text": "<text>"
    },
    "name": "humanize_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe text to humanize. Minimum 20 words (shorter text is returned unchanged at no charge); maximum set by the API key (1000 words by default).
toneNoWriting tone. Omit, or use 'balanced' (equivalent), for the default style with no tone rewrite.
modelNoHumanizer model. Defaults to ghost-3 (latest). ghost-2 is the previous model.
ultraNoUltra: the best version of the text, with peak detection odds and quality. Works with every tone. Takes longer than a standard run (typically 15 to 30 seconds) and is charged 3 words per input word. Defaults to false; turn it on when the user asks for Ultra or for the best possible result.
markdownNoFormat the output as Markdown (headers, lists). Defaults to false: plain text.
spellingNoEnglish spelling variant for the output. Defaults to us. English text only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"Humanizer model. Defaults to ghost-2 (latest)."New value: +"Humanizer model. Defaults to ghost-3 (latest). ghost-2 is the previous model."
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "ghost-2",
      -  "ghost-1"
      -]New value: +[
      +  "ghost-3",
      +  "ghost-2"
      +]
    • changedInput schema / properties / text / description
      Previous value: -"The text to humanize. Minimum 5 words; maximum set by the API key (1000 words by default)."New value: +"The text to humanize. Minimum 20 words (shorter text is returned unchanged at no charge); maximum set by the API key (1000 words by default)."
    • changedInput schema / properties / tone / enum
      Previous value: -[
      -  "academic",
      -  "balanced",
      -  "conversational",
      -  "formal",
      -  "creative"
      -]New value: +[
      +  "academic",
      +  "balanced",
      +  "conversational",
      +  "formal"
      +]
    • addedInput schema / properties / ultra
      Added value: +{
      +  "description": "Ultra: the best version of the text, with peak detection odds and quality. Works with every tone. Takes longer than a standard run (typically 15 to 30 seconds) and is charged 3 words per input word. Defaults to false; turn it on when the user asks for Ultra or for the best possible result.",
      +  "type": "boolean"
      +}
    • removedInput schema / properties / ultra_stealth
      Removed value: -{
      -  "description": "Stronger restructuring for maximum detector evasion. Ignored when tone is conversational, formal or creative.",
      -  "type": "boolean"
      -}
  2. Changed1 schema field changed
    • changedInput schema / properties / markdown / description
      Previous value: -"Preserve markdown formatting in the output. Defaults to true."New value: +"Format the output as Markdown (headers, lists). Defaults to false: plain text."
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare the generic non-read-only, non-destructive, non-idempotent profile; the description adds substantive behavior the annotations cannot convey: the output is only the rewritten text, it must be shown verbatim without critique, and each call consumes account balance at 1 word per input word (3x with ultra). That cost/consumption disclosure is exactly the kind of consequence an agent needs before invoking a billable, non-idempotent operation.

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?

Three sentences, front-loaded with the purpose, then the output contract, then cost — a sensible order with little waste. The parenthetical clarifying that rougher phrasing is intentional earns its place, though the ultra cost note mildly duplicates the schema's own description.

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 six parameters, 100% schema coverage, and no output schema, the description correctly fills the biggest gap by specifying the return value (rewritten text only) and the required presentation behavior. It stops short of covering failure modes (e.g., text under 20 words, over-limit input) or latency in the description, though the schema handles those cases.

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%, with enums and defaults documented for text, tone, model, ultra, markdown, and spelling, so the schema already carries parameter meaning. The description only echoes one schema fact (ultra's 3-words-per-input-word charge) and adds no syntax, interaction, or edge-case detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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?

"Rewrite AI-generated text so it reads like natural human writing and scores as human on AI detectors" names a specific verb (rewrite), the input resource (AI-generated text), and the concrete outcome, even listing the detectors (GPTZero, Originality.ai, Copyleaks, Turnitin) that define success. This is unmistakable against the only sibling, get_account_status, which is a read-only billing lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives strong guidance on what to do with the result ("show it to the user verbatim, without commenting on its quality or editing it"), which is genuine usage direction. However, it offers no explicit when-to-use/when-not framing relative to alternatives, and the only conditional guidance ("turn it on when the user asks for Ultra") lives in the schema rather than the description. Usage is implied by the input type rather than stated.

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.

Resources