Skip to main content
Glama
io.github.xngg1021/academic-research-kernel

io.github.xngg1021/academic-research-kernel

by xngg1021

academic_double_blind_sanitize

Scan manuscripts or directories for double-blind anonymity leaks—PDF metadata, paths, Git credentials, acknowledgments, forbidden tokens—without modifying files; redact matches in output.

Instructions

Read-only scan of a manuscript or reproduction directory for double-blind anonymity leaks (PDF metadata, local paths, Git credentials, unblinded acks, forbidden tokens). Never modifies files and redacts matched forbidden tokens in output.

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": {
      "target_path": "<target_path>"
    },
    "name": "academic_double_blind_sanitize"
  }
}

Input Schema

NameRequiredDescriptionDefault
target_pathYesManuscript file or directory to scan
forbidden_tokensNoOptional list of author/affiliation/repo tokens to flag and redact

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the behavioral burden, and it does well on the safety side: it explicitly states the tool never modifies files and redacts matched forbidden tokens in its output. However, it says nothing about what the findings look like (locations, severity, per-file grouping), whether scanning is recursive, or how long large directories take, so mutation-safety is covered but output behavior is not.

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?

Two tight sentences with the read-only guarantee and redaction behavior front-loaded after the purpose statement; every clause adds information. Minor density cost from the parenthetical list, but no filler.

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 two-parameter, no-annotations, no-output-schema tool, the definition covers purpose, scope, safety posture, and redaction behavior, which is close to sufficient. The remaining gap is how results are reported, which the missing output schema forces into the description and which the description does not supply.

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 both target_path and forbidden_tokens are already documented in the schema, and the description adds no syntax, format, or matching-rule detail beyond mentioning forbidden tokens as a leak class. Baseline 3 is appropriate when the schema does the semantic work.

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 names a specific action (read-only scan) and resource (manuscript or reproduction directory) and enumerates the exact leak classes it hunts: PDF metadata, local paths, Git credentials, unblinded acks, forbidden tokens. That enumeration distinguishes it clearly from generic lint or verification siblings, though it never names an alternative tool directly.

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?

The stated scope (double-blind anonymity checking on a manuscript or reproduction directory) implies the when-to-use context, but there is no explicit when-not guidance and no named alternative such as academic_pre_submission_lint for broader pre-submission checks. An agent can infer usage but must decide on its own which sibling to run first.

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