Skip to main content
Glama

jdx_search

Search JVM code symbols by glob, regex, or fuzzy name across types, packages, and modules; scan methods and fields by setting the symbol kind.

Instructions

Search symbols by glob, regex or fuzzy name. Default kind=all covers types, packages and modules; pass kind=method|field to scan members. A default-kind miss hints at --kind method.

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": "jdx_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
inNoOnly matches from artifacts whose label matches this glob.
kindNoSymbol kind: all, type, class, interface, enum, record, annotation, object, companion, method, field, package or module (default all = types+packages+modules; method|field required to scan members).
fuzzyNoLevenshtein fallback when nothing matches.
limitNoMaximum rows shown (default 50); the rest become a truncation footer.
queryYesThe symbol reference, type, pattern or glob the command asks about. Quote refs containing # or (). Empty only where the command allows it (ls, tree).
regexNoTreat the pattern as a regex.
packageNoOnly symbols under this package.
workspaceNoNamed workspace to answer from (default: the workspace the server was started with). Stored workspaces only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.7.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden, and it does contribute a real behavioral detail: a default-kind miss indicates members exist and should be rescanned with kind=method. However, it says nothing about permissions, whether results are cached or how exhaustive the scan is, or what the response looks like beyond the limit truncation footer covered in the schema. It omits output shape and ordering, which matter for an 8-parameter search.

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 short sentences, front-loaded with the core action, then the kind semantics, then the fallback hint. Nothing is padded. Minor deduction: the closing line references a CLI flag (--kind method) rather than the tool's own parameter name, which is slightly awkward phrasing in an MCP context.

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

Completeness3/5

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

This is a complex tool: 8 parameters, one required, no annotations and no output schema. The description covers the kind dimension well but says nothing about how query, regex and fuzzy interact (are they mutually exclusive?), what workspace and package scoping mean, or what the result rows contain. Given the absence of annotations, a description this terse leaves the agent to learn several behaviors from the schema 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 description coverage is 100%, so every parameter is already documented in the input schema, and the description largely restates the kind semantics that the schema spells out. The one piece of added meaning is the diagnostic hint about a default-kind miss pointing to --kind method, which the schema does not convey. That is a modest addition over a schema that is already self-sufficient.

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 states a specific verb and resource: search symbols, with the accepted matching modes (glob, regex, fuzzy name). It is clearly a symbol-search tool rather than a call-graph or documentation tool, though it never names or contrasts a sibling such as jdx_usages or jdx_literals, so its distinctness is established only by implication.

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?

It gives concrete selection guidance for the most consequential option: default kind=all covers types, packages and modules, while kind=method|field is required to scan members. That is genuine when-to-use advice for one parameter, but there is no guidance on when to prefer this tool over jdx_usages, jdx_literals or jdx_resolve, and no when-not conditions.

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