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

fix_gherkin

Read-only

Fix Gherkin syntax warnings from a jira_to_test_suite result. Takes the current gherkin text and the _gherkin_warnings array, calls your LLM to fix ONLY the flagged issues (adds missing Given/When/Then steps, etc.), and returns the corrected Gherkin. Lightweight — uses ~300-500 tokens vs ~5k for a full regeneration. Requires BYOK LLM key.

Input Schema

Name	Required	Description
`model`	Yes	LLM model to use for the fix, e.g. "gpt-4o-mini". Must belong to the provider whose key you passed in api_key.
`api_key`	Yes	Your own LLM provider API key (BYOK) — OpenAI "sk-…", Anthropic "sk-ant-…", Google "AIzaSy…", or Groq "gsk_…". There is no server-side key for this tool: if you do not have one, do not call it and do not invent a value — placeholders like "configured", "your_api_key" or a masked "sk-…***…" are rejected. Used for this call only, never stored.
`gherkin`	Yes	The current Gherkin text from the jira_to_test_suite result (test_suite.gherkin).
`warnings`	Yes	The _gherkin_warnings array from the jira_to_test_suite result.

Output Schema

Name	Required	Description	Default
`latency_ms`	No
`model_used`	No
`fixed_gherkin`	No
`warnings_after`	No
`warnings_before`	No
`remaining_warnings`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "api_key": "<your-api-key>",
+    "gherkin": "Feature: Login\n  Scenario: ok\n    given I open the page\n    Then I see the form",
+    "model": "gpt-4o-mini",
+    "warnings": [
+      "Step keyword \"given\" should be capitalised"
+    ]
+  }
+]

Changed2 schema fields changedJul 31, 2026

changedInput schema / properties / api_key / description

Previous value: -"Your LLM provider API key."New value: +"Your own LLM provider API key (BYOK) — OpenAI \"sk-…\", Anthropic \"sk-ant-…\", Google \"AIzaSy…\", or Groq \"gsk_…\". There is no server-side key for this tool: if you do not have one, do not call it and do not invent a value — placeholders like \"configured\", \"your_api_key\" or a masked \"sk-…***…\" are rejected. Used for this call only, never stored."

changedInput schema / properties / model / description

Previous value: -"LLM model to use for the fix, e.g. \"gpt-4o-mini\"."New value: +"LLM model to use for the fix, e.g. \"gpt-4o-mini\". Must belong to the provider whose key you passed in api_key."

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "fixed_gherkin": {
+      "type": "string"
+    },
+    "latency_ms": {
+      "type": "number"
+    },
+    "model_used": {
+      "type": "string"
+    },
+    "remaining_warnings": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "warnings_after": {
+      "type": "number"
+    },
+    "warnings_before": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

AddedJun 5, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=true; the description corroborates by disclosing the external LLM call, the BYOK key requirement, and a concrete cost estimate (~300-500 tokens), plus the return ('corrected Gherkin'). It does not describe failure behavior (invalid key, unfixable warnings) or whether output is validated after fixing.

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?

Three front-loaded sentences: what it does, the constraint on scope ('ONLY the flagged issues'), then the cost and key prerequisite. No filler and no repetition of field-level details already in the schema.

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?

With annotations, a full output schema, and 100% parameter coverage already in structured fields, the description covers the remaining agent-relevant context: provenance of inputs, scope of the fix, cost, and the BYOK prerequisite. Minor omission: what happens when warnings is empty or the key is invalid.

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 description coverage is 100% and each parameter is already documented, including BYOK key formats and model/provider pairing. The description only restates that gherkin and warnings come from the jira_to_test_suite result, adding no format or edge-case detail beyond the schema — the 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?

States a specific verb+resource ('Fix Gherkin syntax warnings') and anchors it to a named upstream artifact ('from a jira_to_test_suite result'). An agent can tell this apart from jira_to_test_suite and generate_test_cases: this is a targeted repair pass, not generation.

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?

Explains it consumes the _gherkin_warnings array from a prior jira_to_test_suite call and fixes ONLY flagged issues, implicitly steering the agent away from full regeneration ('~300-500 tokens vs ~5k for a full regeneration'). It does not name the regeneration sibling explicitly or state when fixing is not appropriate, so it falls short of a 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.