Skip to main content
Glama
sunilgentyala

aegis-integrity

by sunilgentyala
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

aegis_analyze_paper

Read-onlyIdempotent

Analyze research papers for plagiarism, AI-generated text, citation errors, and guideline compliance. Provides results for human review of integrity concerns.

Instructions

Run the full AEGIS integrity check on a paper (PDF/DOCX/TEX/TXT).

Covers n-gram and semantic plagiarism against the local corpus, AI-content
detection calibrated for non-native English writers, Crossref citation
verification, LLM watermark heuristics, stylometric ghostwriting
profiling, self-plagiarism, semantic coherence, venue verification,
equation checks and grammar checks. Results support human review; they
are not a finding of misconduct.

Args:
    file_path: Absolute path to the paper file.
    prior_works_dir: Optional folder of the author's own earlier papers
        (for the self-plagiarism check).
    skip_ai_detection: Skip the GPT-2 based AI detector (faster, no model download).
    skip_citations: Skip Crossref lookups (fully offline).
    check_guidelines: Comma-separated subset of IEEE,ACM,BCS,IET,ISACA,ELSEVIER,
        or "all". Empty skips the guideline section.
    html_report: Save a self-contained HTML report. Default True.

Input Schema

NameRequiredDescriptionDefault
file_pathYes
html_reportNo
skip_citationsNo
prior_works_dirNo
check_guidelinesNo
skip_ai_detectionNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.3.2

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent and non-destructive behavior, so the bar is lower; the description still adds real context by noting that results are for human review and not a misconduct finding, and that skip_citations makes the run 'fully offline' while skip_ai_detection avoids a model download. It does not disclose expected runtime or corpus-size dependencies for such a heavy multi-stage analysis.

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?

The opening sentence front-loads the core action, and the ten-item check catalog, while dense, is genuinely informative for scope. The Args block is somewhat verbose relative to what the schema already names, but nothing is padding.

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?

With an output schema present, return values need not be described, and annotations cover the safety profile, so the remaining burden is scope, parameters and caveats — all of which are addressed. Only runtime expectations and the destination of the HTML report are unaddressed.

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 description coverage is 0%, so the description must carry the load — and the Args block documents all six parameters, including the enumerated guideline bodies (IEEE, ACM, BCS, IET, ISACA, ELSEVIER or 'all'), the purpose of prior_works_dir, and the effect of each skip flag. Gaps remain: it does not say where the HTML report is written or that file_path must already exist, though the 'absolute path' guidance is present.

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?

States a specific verb and resource ('Run the full AEGIS integrity check on a paper') plus the accepted file formats, and the word 'full' implies it aggregates the narrower sibling checks. It never names a sibling (e.g. aegis_check_citations, aegis_check_guidelines), so the differentiation from those tools is left to inference rather than stated.

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?

Coverage of what the tool does is thorough, but there is no explicit when-to-use vs. when-to-use-an-alternative guidance. The skip_ai_detection / skip_citations flags imply how to trade completeness for speed or offline operation, which is useful implied usage, but the agent is not told when a narrow sibling tool would be preferable over the full sweep.

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

Deploy Server

Other Tools