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

find_tool

Read-onlyIdempotent

Search available MCP tools by keyword or category before calling them. Returns names, descriptions and, on request, inputSchemas. Queries are logged 90 days, screened for credentials and personal data. Categories: data, dev, encoding, eval, integrations, llm, meta, qa, rag, security, text, web.

Input Schema

Name	Required	Description
`query`	Yes	Keywords, e.g. "cors", "token", "vector", "json"
`category`	No	Optional filter, one of the categories above. Any other value is refused.
`max_results`	No	Maximum tools to return (default 10, max 50). Best match first.
`with_schema`	No	Set true to include inputSchema in results (default: false)

Output Schema

Name	Required	Description	Default
`hint`	No
`tool`	No
`count`	No
`query`	No
`score`	No
`tools`	No
`category`	No
`truncated`	No
`total_matches`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 5, 2026

changedInput schema / properties / category / description

Previous value: -"Optional: filter by category — data | encoding | text | llm | qa | rag | dev | security | web"New value: +"Optional filter, one of the categories above. Any other value is refused."

changedInput schema / properties / max_results / description

Previous value: -"Maximum tools to return (default 10, max 50). Results are ranked by IDF-weighted relevance, so common words like \"test\" do not inflate the list."New value: +"Maximum tools to return (default 10, max 50). Best match first."

changedInput schema / properties / query / description

Previous value: -"Keyword(s) to search in tool name and description (e.g. \"cors\", \"token\", \"vector\", \"json\")"New value: +"Keywords, e.g. \"cors\", \"token\", \"vector\", \"json\""

Changed1 schema field changedOct 31, 2026
- addedInput schema / examples
```
Added value: +[
+  {
+    "query": "leaked api key"
+  }
+]
```

Changed3 schema fields changedJul 29, 2026

addedInput schema / properties / max_results

Added value: +{
+  "description": "Maximum tools to return (default 10, max 50). Results are ranked by IDF-weighted relevance, so common words like \"test\" do not inflate the list.",
+  "type": "number"
+}

addedOutput schema / properties / total_matches
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / truncated
```
Added value: +{
+  "type": "boolean"
+}
```

Changed1 schema field changedJul 7, 2026

changedInput schema / properties / category / description

Previous value: -"Optional: filter by category â€” data | encoding | text | llm | qa | rag | dev | security | web"New value: +"Optional: filter by category — data | encoding | text | llm | qa | rag | dev | security | web"

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "category": {},
+  "count": {
+    "type": "number"
+  },
+  "hint": {},
+  "query": {},
+  "score": {},
+  "tool": {},
+  "tools": {
+    "type": "array"
+  }
+}

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

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds material context the annotations do not: the 90-day query logging, screening for credentials and personal data, and the fact that inputSchemas are only returned on request. It does not state error behavior beyond what the schema notes about refused categories, which keeps it from a 5.

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?

Three dense sentences, front-loaded with the action and the return shape, then the privacy note, then the category list. Nothing is padded, though the logging sentence interrupts the flow between returns and categories.

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?

An output schema exists, so return structure need not be described; all four parameters are documented at 100% and the category vocabulary is supplied in the description. Combined with annotations covering safety and the added privacy disclosure, an agent has everything needed to call this correctly.

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 earns an extra point by enumerating the twelve valid category values that the schema only refers to as "one of the categories above" (enums count is zero). It otherwise restates defaults already documented per-parameter.

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 and resource -- search MCP tools -- plus the scope of the search (keyword or category) and what it returns (names, descriptions, optionally inputSchemas). An agent can distinguish it from siblings like rate_tool or model_info without opening the schema, since it is the only discovery tool in the list.

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?

"Search available MCP tools ... before calling them" gives clear situational context: use it as a discovery step prior to invocation. There are no explicit exclusions or named alternatives, so it sits at 4 rather than 5.

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.