AI humanizer for MCP clients. Rewrites AI text so it reads naturally and sounds human.
Scored across 2 tools
The two tools have completely distinct purposes: checking account status versus humanizing text. There is no overlap or ambiguity in when to use each tool.
Both tool names follow a consistent snake_case verb_noun pattern: get_account_status and humanize_text. The convention is predictable and easy to parse.
Two tools is on the thin side for a typical MCP server, even though this domain is narrow. It covers the minimum viable surface but feels borderline minimal.
Core functionality is present: checking balance/limits and performing the main humanization action. Minor gaps exist around usage history or account management, but agents can operate without them.
Check the UndetectedGPT account linked to this API key: remaining word balance, per-request word limit and per-minute rate limit.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, covering the non-mutating nature. The description adds useful context beyond this by clarifying that the account is tied to the API key and that the tool reports balance and rate limits, which helps set agent expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that starts with the action verb 'Check' and immediately gives the resource and the relevant output fields. There is no filler or redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters, no output schema, and read-only annotations, the description is sufficient for an agent to invoke it correctly. It names the account context and all reported values, leaving no major operational gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters and the input schema is empty, so there is no parameter-level semantics for the description to add. The baseline of 4 applies; the description correctly focuses on the tool's behavior instead.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Check the UndetectedGPT account linked to this API key'. It also lists the exact data returned—word balance, per-request word limit, and per-minute rate limit—making it easily distinguishable from the sibling humanize_text.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool: when an agent needs account quota or rate-limit information. It does not explicitly name alternatives, but the sibling humanize_text is clearly different in purpose, so selection is unlikely to be ambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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).
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The text to humanize. Minimum 5 words; maximum set by the API key (1000 words by default). | |
| tone | No | Writing tone. Omit, or use 'balanced' (equivalent), for the default style with no tone rewrite. | |
| model | No | Humanizer model. Defaults to ghost-2 (latest). | |
| markdown | No | Format the output as Markdown (headers, lists). Defaults to false: plain text. | |
| spelling | No | English spelling variant for the output. Defaults to us. English text only. | |
| ultra_stealth | No | Stronger restructuring for maximum detector evasion. Ignored when tone is conversational, formal or creative. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations only covering generic safety flags (readOnly/destructive/idempotent all false), the description adds real context: the output is intentionally less polished, must be presented verbatim without edits, and consumes the account balance at 1 word per input word. It omits failure modes, limits, and rate-limit behavior, so not a full 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with the core purpose before the output-handling and billing details. Dense but every clause (verbatim display, intentional phrasing, billing unit) carries operational weight; only the long detector list is marginally verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description correctly specifies the return value ('only the rewritten text') and how to present it. Combined with full schema coverage of all six parameters, an agent has everything needed to invoke and consume the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter including tone, model, markdown, spelling, and ultra_stealth is already documented in the schema. The description adds only a tangential link between word count and billing, which does not deepen parameter meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (rewrite) and resource (AI-generated text) with the outcome goal (reads naturally, passes AI detectors like GPTZero and Turnitin). It is unmistakably distinct from the unrelated sibling get_account_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives clear post-call handling rules - show output verbatim, do not comment on quality or edit it - and notes the cost model, so the agent knows how to consume the result. It stops short of explicit when-not-to-use conditions, though no competing sibling exists to route against.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
humanize_text1 field changedInput schema / properties / markdown / descriptionPrevious value: -"Preserve markdown formatting in the output. Defaults to true."New value: +"Format the output as Markdown (headers, lists). Defaults to false: plain text."get_account_statushumanize_textTransform AI-generated text into natural, human-sounding content that bypasses AI detectors.
Rewrite AI-generated text so it reads as human, in a persona's voice.
Text generation over MCP: prose, emails, blog outlines, SQL, humanizing, text diffs, fake data.
Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.
Add one secure layer between your agents and this server.
