Skip to main content
Glama

Lazynext AI Slop Checker

judge

Run the judgement checklist (--judge) over text, HTML, or a directory: the 5-question review (purpose/audience/decision/variety/defaults) with machine-flagged signals per question, a craft-floor gate (contrast/alignment/text-hierarchy/spacing/no-fake-data/no-decorative-effects) mapped from scanner evidence with human-checkbox items for the non-machineable parts, refusal scaffolds, and a machine-computed PASS | REVIEW | REFUSE verdict computed ONLY from machine-verifiable parts. Same input always gives the same verdict.

Input Schema

NameRequiredDescriptionDefault
dirNodirectory path to judge — local filesystem access only
htmlNoHTML document to judge
textNoplain text to judge

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does real work: it discloses determinism ('Same input always gives the same verdict'), that the verdict is computed ONLY from machine-verifiable parts, and that non-machineable criteria become human-checkbox items. It does not state side effects, read-only status, or whether a report file is written, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, but delivered as one very long sentence dense with coined jargon (craft-floor gate, refusal scaffolds, machine-flagged signals). Every clause carries information, yet the lack of sentence breaks and prioritization makes it harder to parse than it needs to be.

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 fairly complex tool with no annotations and no output schema, the description covers the returnable artifacts (per-question flags, gated evidence mapping, checkbox items, PASS|REVIEW|REFUSE verdict) and the determinism guarantee. Missing is output format/shape (JSON vs report) and any error behavior for unreadable directories.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, and the description adds the exclusive-choice framing ('text, HTML, or a directory') that matches the oneOf constraint, signaling one input mode at a time. It does not explain directory traversal depth or HTML handling nuances beyond the schema, so a modest bump to 4 rather than higher.

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?

Specific verb+resource: 'Run the judgement checklist (--judge) over text, HTML, or a directory', followed by an enumeration of what the checklist contains (5-question review, craft-floor gate, refusal scaffolds, verdict). An agent can tell this is an evaluation/judging tool rather than a scanner or rewriter. It stops short of naming a sibling such as scan_text or rewrite_text to contrast against, so it lands at 4.

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?

Input modes are clear (text, HTML, or a directory), which implies when the tool applies, but there is no explicit when-to-use vs when-not guidance and no reference to the scan_* or rewrite_text siblings. The agent must infer that judging follows scanning and differs from plain scanning.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.