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

build_rag_prompt

Read-onlyIdempotent

Assemble a complete RAG (Retrieval-Augmented Generation) prompt from retrieved context chunks and a user query. Handles token budgeting, citation numbering, system instruction injection, and source attribution.

Input Schema

Name	Required	Description
`query`	Yes	The user question to answer
`chunks`	Yes	Retrieved context chunks with .text (required), .source (optional), .score (optional)
`language`	No	Response language instruction (e.g. "French", "Spanish")
`cite_sources`	No	Add [1], [2] citation numbers (default: true)
`max_context_tokens`	No	Max tokens for context section (default: 2000)
`system_instruction`	No	Custom system instruction (default: standard RAG grounding instruction)

Output Schema

Name	Required	Description	Default
`prompt`	No
`system_prompt`	No
`chunks_included`	No
`included_chunks`	No
`chunks_truncated`	No
`total_tokens_estimate`	No
`context_tokens_estimate`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "chunks": [
+      {
+        "source": "a.md",
+        "text": "c1 text"
+      }
+    ],
+    "query": "q?"
+  }
+]

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "chunks_included": {
+    "type": "number"
+  },
+  "chunks_truncated": {
+    "type": "number"
+  },
+  "context_tokens_estimate": {
+    "type": "number"
+  },
+  "included_chunks": {},
+  "prompt": {},
+  "system_prompt": {},
+  "total_tokens_estimate": {
+    "type": "number"
+  }
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

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

First observedMay 26, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description then adds real behavioral value beyond that: it discloses that the tool actually performs token budgeting, injects a system instruction, numbers citations, and attributes sources — transformations the agent would otherwise not know happen inside the call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero waste: the first states what is built and from what, the second enumerates the four processing behaviors. Front-loaded and appropriately sized for the tool's complexity.

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?

Return values are covered by the output schema and safety by the annotations, so the description only needs to explain the transformation, which it does. Minor gaps: it does not say whether low-score chunks are dropped when the token budget is exceeded, or how chunks are ordered before numbering.

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 100%, so the baseline is 3, but the description's feature list maps onto the optional parameters and adds meaning — 'token budgeting' tells you max_context_tokens actually truncates context, and 'citation numbering' tells you cite_sources changes the output text, not just metadata. It does not clarify how chunk.score is used (ordering/filtering), which is the one semantic gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (assemble) and resource (RAG prompt) plus the exact inputs (retrieved chunks + user query), which clearly separates it from prompt_template_fill or system_prompt_builder. It stops short of explicitly naming a sibling it supersedes, so an agent still has to infer its place among prompt/context tools.

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?

Usage is implied by the phrase 'from retrieved context chunks and a user query' — use it when you already have retrieval results. There is no explicit when-not, no mention of where it sits relative to split_chunks, rag_relevance_rank, or truncate_to_tokens, and no prerequisites stated.

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.