Multilingual profanity and toxicity detection. Supports English, Arabic (Gulf dialect aware), Spanish, and French. Returns toxicity score, flagged words with categories (hate/sexual/violence/slur), severity rating, and cleaned text.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to check for profanity (max 10,000 chars) | |
| language | No | Language code: en, ar, es, fr (auto-detected if not provided) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the responsibility of disclosing behavior. It clearly states what the tool returns: toxicity score, flagged words with categories, severity rating, and cleaned text. This gives a good understanding of the output and implies a read-only detection operation, though it doesn't mention potential error cases or rate limits, which are not expected for a detection tool.
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 concise, consisting of two sentences that efficiently convey the tool's purpose, language support, and output. There is no redundant information or filler; every word contributes to understanding the tool.
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 that there is no output schema, the description appropriately outlines the return value (toxicity score, flagged words, severity rating, cleaned text) and language support. It provides sufficient context for a user to understand the tool's capabilities and expected results, though it doesn't dive into edge cases or detailed severity scales, which are not critical for typical usage.
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?
The input schema already provides descriptions for both parameters (text and language), covering 100% of them. The description adds some context, such as multilingual support and 'Gulf dialect aware,' but this is already hinted at in the schema's language description. No additional meaning is added beyond what the schema conveys, so the baseline of 3 is appropriate.
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 clearly states the tool's purpose: 'Multilingual profanity and toxicity detection.' It uses a specific verb ('detection') and a clear resource (profanity/toxicity), and it distinguishes itself from sibling tools by its focus on profanity filtering rather than sentiment or translation.
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 that this tool is for profanity and toxicity detection, and it specifies supported languages (English, Arabic with Gulf dialect awareness, Spanish, French). While it doesn't explicitly mention when not to use it or alternatives, the purpose is unambiguous enough that a user would know to select it for profanity filtering tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have overlapping functionality, such as domain_infra, company_report, and due_diligence all covering DNS/WHOIS/SSL checks. Similarly, web_scrape and scrape_structured both extract website content, and verify_email overlaps with email_audit on DNS-based email checks. This creates ambiguity in tool selection, especially for agents looking for a specific type of analysis.
All tool names use lowercase with underscores, which provides a consistent style. However, the grammatical pattern varies: some are verb-object (verify_email, currency_convert), some are noun-noun (domain_infra, site_audit), and others are adjective-noun (arabic_sentiment, brand_scout). This is not chaotic, but it lacks a rigid verb_noun convention, making it slightly less predictable.
With 25 tools, this sits at the upper boundary of what is considered 'heavy' but is still usable. The server covers a wide range of domains (Arabic NLP, web scraping, domain/email analysis, finance, faith), so the count is justified to a degree, but agents may be overwhelmed by choice. It is borderline appropriate for such a broad utility server.
The tool surface covers many common operations (scraping, DNS checks, email verification, financial data), but there are notable gaps. For example, no generic translation tool exists, only Arabizi-to-Arabic, and there is no text generation or embedding. While the set is extensive, it is not fully comprehensive for the diverse domains it touches, leaving some obvious missing operations.