Java Inspector

search_class

Locate Java classes in Maven dependencies via a live partial index, then scan only relevant JARs. Filter by coordinates, JAR path, or workspace to find classes without waiting for background scans.

Instructions

Search the live partial index, then foreground-scan only relevant JARs without waiting for background scan completion.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_class"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	No		balanced
`limit`	No
`query`	Yes
`format`	No	Output format.	text
`jarPath`	No	Absolute path to an exact JAR. Fastest selector.
`includeJdk`	No
`coordinates`	No	groupId:artifactId[:version[:classifier]].
`jarDirectory`	No	Absolute directory to search for a JAR on demand.
`jarNamePrefix`	No	JAR basename prefix.
`workspacePath`	No	Absolute Java workspace path. Maven is optional.

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv3.0.0Aug 28, 2026

addedInput schema / properties / coordinates

Added value: +{
+  "description": "groupId:artifactId[:version[:classifier]].",
+  "type": "string"
+}

changedInput schema / properties / format / description

Previous value: -"Output format. Default is text (human-readable). Use json for structured machine-readable data. Use toon for Token-Oriented Object Notation — a compact, LLM-friendly format that reduces tokens by ~40% compared to JSON while preserving structure (https://github.com/toon-format/toon)."New value: +"Output format."

addedInput schema / properties / includeJdk

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / jarDirectory

Added value: +{
+  "description": "Absolute directory to search for a JAR on demand.",
+  "type": "string"
+}

addedInput schema / properties / jarNamePrefix

Added value: +{
+  "description": "JAR basename prefix.",
+  "type": "string"
+}

addedInput schema / properties / jarPath

Added value: +{
+  "description": "Absolute path to an exact JAR. Fastest selector.",
+  "type": "string"
+}

removedInput schema / properties / limit / description

Removed value: -"Maximum number of results to return"

addedInput schema / properties / mode

Added value: +{
+  "default": "balanced",
+  "enum": [
+    "fast",
+    "balanced"
+  ],
+  "type": "string"
+}

removedInput schema / properties / projectPath

Removed value: -{
-  "description": "Maven project root directory path",
-  "type": "string"
-}

removedInput schema / properties / query / description

Removed value: -"Search query (partial class name, e.g. \"ObservationRegistry\", \"JpaRepository\", or \"QueryBizOrderDO\")"

addedInput schema / properties / workspacePath

Added value: +{
+  "description": "Absolute Java workspace path. Maven is optional.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "query",
-  "projectPath"
-]New value: +[
+  "query"
+]

First observedv2.3.2May 26, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the behavioral burden and at least reveals the two-phase execution and non-blocking intent ('live partial index', 'foreground-scan only relevant JARs'). It does not disclose output behavior, freshness limits of the partial index, or any side effects, but for a search operation this is a reasonable partial disclosure.

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?

A single, front-loaded sentence with no filler; every phrase ('live partial index', 'foreground-scan only relevant JARs') adds distinct information. It is concise while still conveying the defining behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having 10 parameters, no annotations, and no output schema, the description gives only the search mechanism and omits return format, supported class-matching behavior, and when the various JAR selectors are appropriate. An agent would still need to infer a lot of call context from parameter names alone.

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 60%, so the schema documents most selectors; the description adds some conceptual context with 'relevant JARs' but does not explain any specific parameter. The critical 'query' parameter lacks a schema description and the tool description does not fill that gap, leaving semantics partially inferred from the name.

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?

The description names a specific action and object: search a live partial index and foreground-scan relevant JARs, which distinguishes it from a plain scan or code search. It relies on the tool name 'search_class' to make the object explicit, and it does not directly contrast with siblings, but the mechanism is concrete.

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?

The phrase 'without waiting for background scan completion' implies a fast-path use case, but the description never states when to choose this over scan_project, find_jar, or search_code, nor does it list exclusion conditions. Usage context is only implied.

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

Deploy Server