IA-QA — 152 QA & Dev Tools for AI Agents

toxicity_scan

Read-onlyIdempotent

Scan text for toxic language, hate speech, bias/stereotype framing, violence, sexual and self-harm content. Lexical + structural pattern matching (identity term + predicate), not a semantic classifier — returns per-category risk plus the named rules that fired, so every finding can be checked. Languages: English for every category; French for insults, coarse language, direct threats and self-harm intent; anything else reads clean, so clean is not proof of safety. Text is also matched after undoing leetspeak and lookalike letters. Self-harm is critical only on a first-person intent — a mention ("call 988 if you have suicidal thoughts") is medium. Useful for LLM safety guardrail testing and triage; signal-only, not a calibrated CI gate.

Input Schema

Name	Required	Description	Default
`text`	Yes	Text to scan
`categories`	No	Categories to check (default: all)

Output Schema

Name	Required	Description	Default
`method`	No
`results`	No
`text_length`	No
`overall_risk`	No
`categories_checked`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "text": "Ce contrat est conclu avec un partenaire."
+  }
+]

Changed1 schema field changedAug 19, 2026
- addedOutput schema / properties / method
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "categories_checked": {
+    "type": "number"
+  },
+  "overall_risk": {},
+  "results": {},
+  "text_length": {
+    "type": "number"
+  }
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedMay 26, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes far beyond the readOnly/idempotent annotations: states the detection method is lexical+structural rather than semantic, discloses per-language coverage gaps ('anything else reads clean, so clean is not proof of safety'), explains leetspeak/lookalike normalization, and gives the specific severity rule for self-harm. This is exactly the kind of behavioral context annotations cannot carry.

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 — coverage and method come first, caveats after — with no filler sentences. It reads as a long run-on block rather than structured clauses, which slightly hurts scannability for an agent parsing it, but every sentence carries information.

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?

For a signal-only scanner with two parameters, the description covers method, language limits, normalization, severity edge cases, and intended use; an output schema exists, so it need not explain return shape, though it helpfully notes findings come with the rules that fired.

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 coverage is 100%, so both `text` and `categories` are already documented, and the description adds little parameter-level detail beyond noting that text is pre-normalized before matching. With the schema doing the heavy lifting, baseline 3 applies.

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?

Names a specific verb and resource ('scan text for toxic language...'), enumerates exactly which categories are covered, and implicitly differentiates from the sibling bias_detect by scoping bias into a broader multi-category scan. An agent knows precisely what this tool does without inspecting the schema.

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?

Explicitly positions the tool ('useful for LLM safety guardrail testing and triage; signal-only, not a calibrated CI gate'), which tells the agent both when to reach for it and when not to rely on it. It stops short of naming sibling alternatives (e.g. bias_detect vs. this tool's bias category), so routing between the two still requires inference.

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

All IA-QA — 152 QA & Dev Tools for AI Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.