Skip to main content

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

by io.github.JcJamet

Overview Discussions Admin

llm_generate

Read-only

Generate text with an open-source model hosted on Groq, on the server's key — no API key needed. Models: openai/gpt-oss-20b, openai/gpt-oss-120b, qwen/qwen3.8-27b (default "openai/gpt-oss-20b"). HuggingFace models are not served on the server key. A reasoning model that spends max_tokens thinking is retried once at 4096. Rate-limited.

Input Schema

Name	Required	Description	Default
`model`	No	Model ID (default: "openai/gpt-oss-20b"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b, qwen/qwen3.8-27b. Other ids from list_llm_models, HuggingFace ones included, are BYOK-only and will be rejected.
`prompt`	Yes	The user prompt / instruction to send to the model
`system`	No	Optional system prompt to set context or persona
`max_tokens`	No	Maximum tokens to generate (default: 2048, max: 4096)
`temperature`	No	Sampling temperature 0.0–1.5 (default: 0.7)

Output Schema

Name	Required	Description	Default
`model`	No
`usage`	No
`content`	No
`provider`	No
`latency_ms`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / model / description

Previous value: -"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b. Other ids from list_llm_models, HuggingFace ones included, are BYOK-only and will be rejected."New value: +"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b, qwen/qwen3.8-27b. Other ids from list_llm_models, HuggingFace ones included, are BYOK-only and will be rejected."

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "prompt": "Reply with the single word OK."
+  }
+]

Changed1 schema field changedOct 28, 2026

changedInput schema / properties / model / description

Previous value: -"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b; HuggingFace: Qwen/Qwen3-32B, meta-llama/Llama-3.3-70B-Instruct, deepseek-ai/DeepSeek-R1, google/gemma-3-27b-it, and more. Other ids from list_llm_models are BYOK-only and will be rejected."New value: +"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b. Other ids from list_llm_models, HuggingFace ones included, are BYOK-only and will be rejected."

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / model / description

Previous value: -"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b, qwen/qwen3.6-27b; HuggingFace: Qwen/Qwen3-32B, meta-llama/Llama-3.3-70B-Instruct, deepseek-ai/DeepSeek-R1, google/gemma-3-27b-it, and more. Other ids from list_llm_models are BYOK-only and will be rejected."New value: +"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b; HuggingFace: Qwen/Qwen3-32B, meta-llama/Llama-3.3-70B-Instruct, deepseek-ai/DeepSeek-R1, google/gemma-3-27b-it, and more. Other ids from list_llm_models are BYOK-only and will be rejected."

Changed1 schema field changedAug 20, 2026

changedInput schema / properties / model / description

Previous value: -"Model ID (default: \"qwen/qwen3-32b\"). Server-keyed whitelist only — Groq: qwen/qwen3-32b, llama-3.3-70b-versatile, meta-llama/llama-4-scout-17b-16e-instruct, llama-3.1-8b-instant; HuggingFace: Qwen/Qwen3-32B, meta-llama/Llama-3.3-70B-Instruct, deepseek-ai/DeepSeek-R1, google/gemma-3-27b-it, and more. Other ids from list_llm_models are BYOK-only and will be rejected."New value: +"Model ID (default: \"openai/gpt-oss-20b\"). Server-keyed whitelist only — Groq: openai/gpt-oss-20b, openai/gpt-oss-120b, qwen/qwen3.6-27b; HuggingFace: Qwen/Qwen3-32B, meta-llama/Llama-3.3-70B-Instruct, deepseek-ai/DeepSeek-R1, google/gemma-3-27b-it, and more. Other ids from list_llm_models are BYOK-only and will be rejected."

Changed1 schema field changedJul 24, 2026

changedInput schema / properties / model / description

Previous value: -"Model ID (default: \"qwen/qwen3-32b\"). Use list_llm_models tool with provider \"Groq\" or \"HuggingFace\" to see available models."New value: +"Model ID (default: \"qwen/qwen3-32b\"). Server-keyed whitelist only — Groq: qwen/qwen3-32b, llama-3.3-70b-versatile, meta-llama/llama-4-scout-17b-16e-instruct, llama-3.1-8b-instant; HuggingFace: Qwen/Qwen3-32B, meta-llama/Llama-3.3-70B-Instruct, deepseek-ai/DeepSeek-R1, google/gemma-3-27b-it, and more. Other ids from list_llm_models are BYOK-only and will be rejected."

Changed1 schema field changedJul 7, 2026

changedInput schema / properties / temperature / description

Previous value: -"Sampling temperature 0.0â€“1.5 (default: 0.7)"New value: +"Sampling temperature 0.0–1.5 (default: 0.7)"

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "content": {},
+  "latency_ms": {
+    "type": "number"
+  },
+  "model": {},
+  "provider": {},
+  "usage": {}
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

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

First observedMay 26, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses the keyless server-key model, a whitelist that rejects unlisted/HuggingFace ids, rate limiting, and a non-obvious retry behavior for reasoning models that exhaust max_tokens (retried once at 4096). No contradiction with readOnlyHint=true, openWorldHint=true, idempotentHint=false.

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?

Front-loads the capability and key constraint, then constraints, then failure modes — four dense sentences with little waste. The model enumeration duplicates the model parameter's schema description, which is the only redundancy.

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 5-param generation tool with full schema coverage, an output schema, and annotations covering safety, nothing material is missing: cost/auth model, allowed models, limits, and retry behavior are all disclosed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so baseline is 3; the description adds real meaning by tying max_tokens to the reasoning-model retry at 4096 and by reinforcing that the model id must be on a server-keyed whitelist. It does not add syntax or interaction detail for temperature or system, so it isn't a 5.

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?

States a specific verb ('Generate text') plus the resource and hosting model ('open-source model hosted on Groq, on the server's key'), and enumerates the exact models available. An agent knows this is free server-keyed text generation, distinct from evaluation/analysis siblings like compare_models or run_semantic_tests.

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?

Gives a clear selection condition ('no API key needed' / server key available) and an explicit exclusion ('HuggingFace models are not served on the server key'), which routes the agent elsewhere for BYOK models. It stops short of naming which sibling to use instead for that case, but the constraint is actionable.

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

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.

Resources