Skip to main content
Glama

Verify Generated Code

verify_generated
Read-onlyIdempotent

Checks generated Java files for TODO comments, raw types, missing nullability annotations, var fields, missing Javadoc, and Object return types before compile/start.

Instructions

Deterministic antislop gate: checks generated Java files for TODO comments, raw types, missing nullability annotations, var in fields, missing Javadoc, and Object return types. Runs as a pipeline gate before Prove (compile + start).

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": {
      "files": "<files>"
    },
    "name": "verify_generated"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYesObject mapping file paths to their content (only .java files are checked)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds meaningful behavior beyond that: it is deterministic (no model judgement), it checks a fixed enumerated rule set, and it occupies a specific position in the pipeline before compilation. It does not disclose what the gate returns on failure or whether it blocks or merely reports, and no output schema exists to fill that gap.

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?

Two sentences, no filler. The rule list is front-loaded and the pipeline placement comes second, which is the correct order of importance. Every clause contributes either a check performed or the stage at which the tool belongs.

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 a one-parameter, annotation-rich, side-effect-free tool this is nearly complete: the agent knows what is checked, on what inputs, and where in the workflow it belongs. The remaining gap is outcome semantics — the absence of an output schema means the description should ideally say what a failing verification looks like, and it does not.

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?

With a single parameter at 100% schema description coverage, the schema already carries the meaning, so the baseline is 3. The description reinforces scope by saying only generated Java files are checked, matching the schema's '.java only' note, but it adds no detail about how the file map is structured or what happens to non-Java entries — the schema itself ambiguously types the map as a string, and the description does not clarify it.

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 ('checks generated Java files') and then enumerates the exact rule set: TODO comments, raw types, missing nullability annotations, var in fields, missing Javadoc, Object return types. The phrase 'deterministic antislop gate' plus the explicit rule list makes it distinguishable from generic siblings like analyze_code or find_todos, since it is a fixed-rule pass rather than a general analyzer.

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?

Gives a clear usage context: it is a pipeline gate that runs before the Prove (compile + start) step, and it applies only to generated Java files. What is missing is any explicit exclusion or named alternative — it never says 'use analyze_code instead when you want semantic analysis' or 'use find_todos for non-generated code', even though find_todos overlaps with the TODO check.

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