Skip to main content
Glama

jdx_diff

Compare two JVM artifacts (old vs. candidate) to detect public-API changes and named binary-compatibility breaks, ordered with breaking changes first.

Instructions

What changed between two artifacts? Public-API diff with named binary-compatibility rules (MEMBER_REMOVED, RETURN_TYPE_CHANGED, ...), most breaking first. query is the OLD artifact and new the candidate; each is a jar, class dir, glob, or Maven coordinate. Exits 0 whenever the comparison ran.

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>",
      "new": "<new>"
    },
    "name": "jdx_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
newYesThe NEW (candidate) artifact, compared against `query`.
limitNoMaximum rows shown (default 200); the rest become a truncation footer.
queryYesThe OLD (baseline) artifact: jar file, class directory, glob, or group:artifact:version.
failOnNonone (default, always 0), breaking (exit 1 on a breaking change) or any (exit 1 on any difference).
severityNoHow much to print: all (default), suspicious (breaking and suspicious), or breaking only. The tally always describes everything.
workspaceNoNamed workspace to answer from (default: the workspace the server was started with). Stored workspaces only.
visibilityNopublic (default: public and protected declarations) or all (every declared type and member).
includeSyntheticNoCompare bridge/synthetic members too, hidden by default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.7.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses result ordering (most breaking first), that exit 0 means the comparison ran, and that failOn overrides that default. It also explains that `severity` only narrows printing while the tally always covers everything, and that truncation adds a footer. Minor gaps remain: it never says whether Maven coordinates are fetched over the network or whether the operation is strictly read-only.

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?

The leading question front-loads the purpose, then four dense sentences cover argument roles, output shape and exit semantics with no filler. Every sentence contributes something an agent would otherwise have to guess.

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?

For an 8-parameter tool with no annotations and no output schema, the description covers ordering, truncation, exit codes and verbosity control well enough to invoke it correctly. It stops short of describing the actual row/result shape beyond 'named rules' and ordering, which would matter given there is no output schema.

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 the baseline is 3 and the schema already documents every parameter including the failOn and severity modes. The description adds little beyond it, mostly restating the query/new roles and generalizing the artifact formats for `new`. That is adequate but not meaningfully additive.

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?

Opens with a specific verb+resource question ('What changed between two artifacts?') and immediately pins down scope: public-API diff with named binary-compatibility rules and breaking changes first. That combination is distinct from every listed sibling (outline, members, usages), so an agent can select it without inspecting the schema.

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 states the roles of both required arguments ('`query` is the OLD artifact and `new` the candidate') and explains when the process will exit non-zero, which is effectively when-to-use guidance for CI-style checks. It does not give explicit exclusions (e.g. when to prefer jdx_annotated or jdx_outline for a single-artifact inspection), so it falls short of a full 5.

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